Pega DX MCP Server

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v1.0.0
Disambiguation3/5
Many tools are clearly distinct, but there are some overlapping purposes (e.g., 'bulk_cases_patch' vs 'perform_bulk_action', 'get_case_action' vs 'get_case_type_action') and similar-sounding tools for different versions (e.g., 'update_case' V1 vs 'perform_case_action' V2) that could cause agent confusion.
Naming Consistency4/5
Most tools follow a verb_noun pattern (e.g., 'create_case', 'get_assignment'), but a few deviate (e.g., 'jump_to_step', 'navigate_assignment_previous'). The pattern is generally predictable and readable.
Tool Count2/5
With 67 tools, the server is excessively large for typical use cases. While the Pega domain is broad, this many tools creates cognitive overload and reduces coherence.
Completeness4/5
The tool set covers nearly all lifecycle operations for cases, assignments, attachments, participants, data views, and more. Minor gaps exist, such as a dedicated 'list assignments for case' tool, but overall coverage is comprehensive.
Average 3.8/5 across 67 of 67 tools scored. Lowest: 2.9/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 0 commits in the last 12 weeks
- Last stable release on March 24, 2026
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is passing
This repository is licensed under Apache 2.0.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description provides no behavioral context beyond the name, e.g., whether this is a read-only operation, what happens if case has no tags, or if case must exist. Minimal value added.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no unnecessary words. Could be restructured to include output details without sacrificing brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema and description does not specify return format. Agent cannot know if tags are returned as array of strings or objects. Missing context for a simple retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage with detailed descriptions for both parameters, especially caseID with example. Tool description adds no additional parameter information, so score stays at baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'get' and resource 'list of tags' associated to a case, distinguishing from siblings like add_case_tags. However, lacks detail on whether tags are simple strings or structured objects.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. Does not mention prerequisites, such as ensuring case exists, nor when add_case_tags or delete_case_tag might be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description should disclose safety and behavior. It implies a read operation but does not confirm read-only, mention pagination, rate limits, or return format. For a tool with no annotations, this is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no redundant words. However, its brevity limits the information conveyed; a slightly longer description could improve clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and absence of an output schema, the description covers the basic action. However, it lacks details on how relatedness is defined (e.g., relationship type) and whether results are paginated, which would aid agent understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed descriptions (e.g., caseID example, sessionCredentials explanation). The description adds no additional parameter context beyond what the schema already provides, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: retrieve a list of related cases for a given case ID. However, among siblings like get_case_ancestors and get_case_descendants, there is no differentiation to explain what 'related' means versus hierarchical relationships.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool over alternatives (e.g., get_case_ancestors) or when not to use it. No prerequisites or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states 'Delete' (destructive) but does not explain side effects, authorization requirements, rate limits, or implications of the 'conditional save plan'. This is insufficient for a destructive operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, concise and front-loaded with the primary action. However, it could be slightly more structured to separate purpose from requirements. Overall, no waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description does not provide enough context about behavior (e.g., what happens on success/failure, handling of conditional save plan, or interaction with credentials). A delete operation with nested parameters needs more completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the schema already provides detailed descriptions for all parameters, including examples for dataViewParameters. The description adds 'Requires primary key(s)' which aligns with schema but does not add significant new meaning beyond structured data.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Delete a data record' and specifies it is for savable Data Pages and data object classes, distinguishing it from other deletion tools like delete_case or delete_attachment. However, it could more explicitly differentiate from sibling tools like update_data_record_full.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions prerequisites (conditional save plan, primary keys) but does not provide guidance on when to use this tool versus alternatives (e.g., when to delete vs. update) or when not to use it. The context is implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavioral traits. It indicates a read operation (retrieving a list) but does not mention authentication requirements (though implied by the input schema), pagination, rate limits, or possible errors. The behavioral transparency is insufficient for safe agent decision-making.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with no unnecessary words. The main action and optional filter are front-loaded, making it easy to grasp quickly. Every sentence adds relevant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there is no output schema, the description should provide more detail about the return format (e.g., structure of metadata, nature of HATEOAS links). The tool has moderate complexity (nested authentication object) and 2 parameters. The description is minimal and does not fully cover what the agent needs to understand the tool's output and usage context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers both parameters with full description coverage (100%). The description adds minimal value by restating the optional filtering for 'type' and provides no additional semantics for 'sessionCredentials' beyond what the schema already explains. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Retrieve') and resource ('list of available data objects'), clearly indicating that the tool returns a list with metadata and HATEOAS links. It also mentions optional filtering by type, which helps distinguish it from more specific sibling tools like get_case or get_attachment. However, 'data objects' remains somewhat generic among siblings that also deal with data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description offers no explicit guidance on when to use this tool versus its siblings. It mentions optional filtering but does not state prerequisites, when not to use it, or alternative tools for specific data object types. The agent is left to infer usage from context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, and the description only mentions it uses 'Get Next Work' functionality. Lacks disclosure of authentication requirements, idempotency, or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences front-loading the purpose with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given full schema coverage and no output schema, the description adequately defines the tool's function but could clarify return details beyond 'detailed information'.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage with good descriptions. The tool description does not add additional meaning beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it retrieves the next assignment for the requestor using Get Next Work, but does not differentiate from sibling tools like get_assignment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., get_assignment). No exclusions or prerequisites provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fails to disclose important behavioral traits such as authentication requirements, side effects, or error behavior. It only mentions the return of metadata with optional UI resources.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at two sentences, front-loaded with purpose, and contains no extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (4 params, nested object, no output schema), the description is somewhat complete but lacks details on return structure, error cases, and prerequisites. It mentions role configuration, permissions, and user details but is vague.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description adds minimal new meaning beyond the schema. For sessionCredentials, schema already provides detailed info. The description hints at return content but not at parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it gets detailed information about a specific participant role, including role configuration, permissions, and user details. However, it does not differentiate from sibling tools like get_participant or get_participant_roles.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites, context, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden but only mentions the basic action. It does not disclose whether duplicates are handled, permissions required, or what happens on failure. This is minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, no wasted words, front-loading the key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks details on return values, error handling, prerequisites (e.g., case existence), and whether followers are appended or replaced. Incomplete for a mutation tool with no output schema or annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so each parameter is already described in the schema. The description adds little beyond restating the action; baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Add multiple followers' and the resource 'work object/case', distinguishing it from sibling tools like delete_case_follower and get_case_followers.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives (e.g., adding followers individually or via other methods). The description only states what it does without context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden for behavioral disclosure. It only states the high-level action without detailing side effects, error conditions (e.g., non-existent relationship), permissions, reversibility, or impact on related data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 13 words, front-loaded with purpose. Every word is necessary and there is no extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a mutation tool, the description is too brief. It does not explain return values, error handling, or prerequisites (e.g., that the relationship must exist). More behavioral context is needed for safe invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all parameters are already documented. The description adds 'by deleting a specific relationship' which reinforces the purpose but does not add new semantic details beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Remove', the resource 'related work association between two cases', and the mechanism 'deleting a specific relationship'. It distinguishes from sibling tools like 'relate_cases' (adds relationship) and 'get_related_cases' (lists relationships).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as 'relate_cases' or 'delete_case_follower'. Context signals show many sibling tools for case operations, but the description does not help the agent choose correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only states 'Retrieves information' (implying read-only) but fails to disclose error behaviors, permissions, rate limits, or empty result handling. Insufficient for a retrieval tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with front-loaded purpose. No redundant information, though could be slightly more efficient by merging the second sentence into the first.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple retrieval tool with 2 well-documented parameters, but lacks output format or behavior details (e.g., empty list vs. error). No output schema means description should compensate, but it does not fully address completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% description coverage. Description adds minor value regarding caseID format ('Complete identifier including spaces') but does not significantly enhance understanding beyond schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb 'Get' and resource 'list of Case Followers' with explicit mention of retrieving users following a case. Differentiates from sibling tools like add_case_followers and delete_case_follower by focusing on read-only retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives (e.g., when to fetch followers vs. add/delete). Only implies usage for receiving notifications, but lacks context on prerequisites or conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description is the sole source for behavioral disclosure. It mentions returning metadata with customizable logic, implying a read-only operation, but does not explicitly state no side effects or authentication requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that directly states the purpose and key details without any extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description should explain return values more thoroughly. 'Returns view metadata with customizable logic' is vague and does not specify structure or content of the response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds minimal additional meaning beyond restating that it uses case ID and view name.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves view details given a case ID and view name, using a specific verb and resource. However, it does not differentiate from the sibling tool 'get_case_view_calculated_fields'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., get_case_view_calculated_fields). No context on prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It fails to disclose whether relationships are bidirectional, idempotent, or require specific permissions. It does not mention side effects or recovery actions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence concisely captures the purpose without extraneous information. It is front-loaded with the verb and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested objects, no output schema) and sibling tools, the description is insufficient. It does not explain what 'relating' means operationally, the return value, or error conditions, leaving the agent underinformed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds context with examples for 'caseID' and clarifies the 'cases' parameter structure, but does not significantly extend beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Create relationships' and specifies the resource ('cases'), and distinguishes from sibling tools like 'create_case' (creates new case) and 'delete_related_case' (removes relationships).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance is provided. It does not mention prerequisites (e.g., cases must exist) or contrast with alternatives like 'get_related_cases' or 'create_case'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description must cover behavioral traits. It describes the action as adding a process and returning details, but lacks warnings about side effects, permission requirements, or irreversible actions. This is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, concise and front-loaded. First sentence conveys primary action and output. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 4 parameters (including nested object) and no output schema, the description provides basic purpose and usage context but lacks details on return structure, error states, and behavioral nuances. Adequate but incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
All 4 parameters have descriptions in the schema (100% coverage). The description does not add extra meaning beyond schema, so baseline 3 applies. No parameter details in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool adds an optional process and returns next assignment details. It differentiates from siblings by specifying 'optional action' and 'case actions', but doesn't explicitly distinguish from similar tools like perform_case_action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides context that it's invoked when a user tries to initiate an optional action, but no when-not-to-use or alternative tools referenced. Siblings include many action tools, but no guidance on choosing this one.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses auto-fetching of eTag but omits critical behaviors like the default cleanup of processes (cleanupProcesses defaults to true) and prerequisites/permissions. The description lacks depth on side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences, front-loading the purpose. A bit more structure could help, but it is efficient and avoids verbosity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of 6 parameters including nested sessionCredentials and no output schema, the description is incomplete. It does not explain return values, error conditions, or the effect of the stage change on the case workflow.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description adds moderate value beyond the schema (e.g., eTag auto-fetch behavior). However, for most parameters like caseID and viewType, the description adds little new information.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Change to a specified stage of a case' using a specific verb and resource. It distinguishes itself from siblings like 'change_to_next_stage' by specifying 'based on stageID passed' and allowing navigation to any valid stage (primary, alternate).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for manual stage selection but does not explicitly state when to use this tool over alternatives like 'change_to_next_stage'. No when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. It mentions the stage constraint but lacks info on consequences, irreversibility, or authentication needs. Destructive aspect is clear but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no waste, directly states action and condition. Perfectly concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 required param, no output schema), description is mostly complete but lacks explanation of behavior when case not in create stage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers both caseID and sessionCredentials with detailed descriptions. Description adds no parameter information, meeting baseline for 100% coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb (delete), resource (case), and condition (in create stage). Distinct from siblings like update_case or other delete tools, though could be more explicit about the restriction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implied usage for cases in create stage, but no explicit guidance on when not to use or what alternatives exist. For a delete operation, this is minimally adequate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description should disclose more behavioral traits. It only states the action without mentioning permanence, permissions, or side effects like whether the tag is deleted from the case only or globally.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with verb and object, no redundant information. However, could be slightly more structured with a brief note on usage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description fails to mention what the tool returns (success/failure messages) or behavior on errors (e.g., tag not found), making it incomplete for a deletion operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema descriptions cover all parameters with examples and details, but the tool description adds no extra semantic value beyond what's already in the schema, resulting in a baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Delete', the resource 'tag from a case', and the identifiers 'case ID and tag ID', distinguishing it from sibling tools like add_case_tags and get_case_tags.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implies usage when a tag needs to be removed from a case, but lacks explicit guidance on prerequisites (e.g., tag must exist) or when not to use this tool vs alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits. It states 'Get' implying read-only, but doesn't explicitly confirm no side effects, required permissions, or authentication details beyond what the schema implies.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the action and includes key output elements ('view metadata and available actions'). No extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested objects, no output schema, many siblings), the description gives a general idea of returns but lacks specifics on output structure, authentication requirements, or preconditions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with well-described parameters. The tool description adds no additional meaning to the parameters, maintaining the baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves detailed information about a case action, including view metadata and available actions. It distinguishes itself from siblings like get_case_action and get_case_type_bulk_action via the focus on case type actions rather than instance-level actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. While the parameter description for actionID suggests using get_case_types as a prerequisite, the tool description itself lacks explicit usage context or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose whether the operation is read-only, any side effects, authentication requirements, rate limits, or data sensitivity. The description only mentions return data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loading the purpose and required parameters, then the return contents. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read tool with 4 parameters and no output schema, the description covers the basics but omits error handling, prerequisites (e.g., case existence), and output structure details that would help an agent understand the response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (all parameters documented in schema). The description merely summarizes the parameters already detailed in the schema, adding no additional semantic value beyond restating the purpose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves detailed participant information using case ID and participant ID, distinguishing it from siblings like create_case_participant, delete_participant, update_participant, and get_participant_roles.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., get_participant_roles for roles only). No exclusion criteria or context provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It only states "Get detailed information" without disclosing side effects, authentication dependencies (beyond sessionCredentials parameter), rate limits, or any operational constraints. The add of "view metadata and available actions" is minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that states the tool's purpose without any wasted words. It efficiently conveys the core function and key information returned.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read-only retrieval tool with 5 parameters (including a nested sessionCredentials object), the description together with the schema covers the essential aspects. It mentions the key elements of the response (view metadata, available actions). However, the absence of an output schema could have been mitigated by a brief description of the return structure, which is not provided.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with detailed descriptions for all parameters, including examples for caseID and actionID. The description adds no further meaning beyond the schema, but given the high coverage, a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb "Get" and the resource "case action", and specifies what information is returned: "detailed information, including view metadata and available actions". This distinguishes it from sibling tools like get_case (case-level) and get_assignment_action (assignment actions), making the purpose specific and actionable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any guidance on when to use this tool versus its many siblings (e.g., get_case, get_assignment_action, perform_case_action). There is no mention of prerequisites, contextual conditions, or when to choose an alternative, leaving the agent without clear decision criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It indicates the tool returns stages with processes, steps, and visited status, implying a read-only operation. However, it does not disclose behavioral traits like authentication requirements, error behavior for invalid case IDs, or whether the response is paginated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise and easily readable. It could be improved by adding a brief usage note, but it is appropriately sized.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a retrieval tool with no output schema and no annotations, the description is adequate but incomplete. It explains the input and output structure but does not mention authentication prerequisites (though sessionCredentials is optional) or potential constraints like case ID format specifics.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond the schema for parameters; it only restates that the tool uses a case ID. The sessionCredentials parameter is well-documented in the schema itself.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a stages list for a given case ID, including processes, steps, and visited status. This is specific and distinguishes it from sibling tools like 'get_case' which retrieves basic case info.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'get_case_action' or 'jump_to_step'. No context on prerequisites, exclusions, or scenarios where other tools are preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the burden of behavioral disclosure. It states the tool validates the documentID, checks user access, and returns base64 content, which gives basic insight into its behavior. However, it omits details like error handling for invalid IDs or unauthorized access, idempotency, or whether the operation is read-only. The description is adequate but not complete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, each sentence adds meaningful information: purpose, mechanism, and validation flow. No redundant words or unnecessary details. It is concise and efficiently communicates the core functionality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (2 parameters, 1 required, no output schema), the description is largely complete. It covers what the tool does, the key parameter, and the behavior (validation, access check, output format). It could mention error responses or size limits, but overall it provides sufficient context for an agent to effectively use the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, meaning the schema already provides detailed descriptions for each parameter (documentID and sessionCredentials). The tool description adds only minor context about validation and access checking. Since the schema carries the load, the description's contribution is minimal, justifying a baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves document content as a base64 string, using the verb 'get' and 'downloads'. It specifies the resource is a document and mentions validation and access checks. However, it does not distinguish itself from the sibling tool 'get_attachment', which likely serves a similar role for attachments, missing an opportunity for differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'get_attachment' or other retrieval tools. It does not mention prerequisites, limitations, or when not to use it. The tool exists among many siblings with similar purposes, but no context is given for appropriate selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavioral traits. It indicates the tool releases a lock and cleans up updates, implying a destructive action, but does not clarify side effects like error handling, idempotency, or prerequisites. Key behavioral details are missing, making it insufficient for safe invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: one sentence defining the action and one sentence on usage context. Every word earns its place without redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters (one nested complex) and no output schema, the description is too brief. It omits return value information, error conditions, and behavioral guarantees (e.g., idempotency). A lock release tool needs more completeness to guide the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed parameter descriptions. The tool description adds no additional semantic value beyond the schema for the parameters. For high schema coverage, baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool releases a pessimistic lock on a Pega case and cleans up cached/pending updates, clearly identifying the action and resource. This distinguishes it from sibling tools like 'perform_case_action' or 'update_case' which don't focus on lock management.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions it is 'used when canceling case operations that require locking', providing some context. However, it does not specify when NOT to use it, nor does it mention alternatives (e.g., other locking/unlocking tools that might exist). The guidance is implied but lacks explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must bear the full burden of behavioral disclosure. It only states the action without explaining side effects (e.g., whether tags are appended or replaced), error conditions, or permission requirements. This lack of detail hinders agent understanding of the tool's impact.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that communicates the core purpose without any fluff. Every word is necessary, and it is front-loaded with the key action and object.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a relatively simple write operation with detailed schema and clear siblings, the description is minimally complete. However, it lacks context on behavior (e.g., idempotency, overwrite behavior) that would fully inform an agent. An output schema could have compensated, but none exists.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with detailed descriptions for each parameter, including formats and constraints. The description adds no additional semantic value beyond the schema. With full schema coverage, a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Add multiple tags to a case' clearly specifies the action (add), the object (tags), and the target (case). It effectively distinguishes the tool from siblings like delete_case_tag (removing tags) and get_case_tags (retrieving tags), which have inverse or different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context but does not explicitly state when to use this tool versus alternatives. Sibling names provide indirect differentiation, but no direct guidance on when to add vs delete or retrieve tags is provided. This is adequate but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the filtering behavior (non-view fields are filtered out). However, it omits details about error handling, side effects, or whether the operation is read-only (implied by name but not stated).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with three sentences, front-loading the main action and adding a behavioral note without superfluous words. It efficiently conveys the core functionality and an important constraint.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested objects, no output schema), the description lacks information about the return format or typical use cases. It covers the input behavior but leaves the output unaddressed, which is a gap for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Since schema description coverage is 100%, the baseline is 3. The description adds minimal extra meaning beyond the schema, only clarifying that fields not in the view are filtered. This slight addition does not significantly enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves calculated fields for a given case view, specifying the verb "Get" and the resource "calculated fields." It distinguishes from sibling tools like get_case_view by focusing on calculated fields and explaining that only requested fields are retrieved and non-view fields are filtered out.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly guide when to use this tool versus alternatives. It lacks context about prerequisites (e.g., must have a view with calculated fields) and does not mention when other tools like get_case_view might be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as side effects, authentication requirements, or whether it's read-only.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences that front-load the purpose and add a supporting detail, with no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks output schema, and the description only vaguely mentions what metadata includes. Could be more complete about the return format or structure, but given the high schema coverage, it is marginally adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage with detailed parameter descriptions, so the baseline is 3. The description adds context about supporting both data view types but does not add significant parameter semantics beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves data view metadata, including parameters and queryable fields, which is distinct from siblings like get_list_data_view (listing) and get_data_view_count (counting).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Mentions support for both queryable and non-queryable data views, which implies when to use, but lacks explicit guidance on when not to use or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It mentions overriding the entire record but does not disclose behavioral traits such as authentication requirements, destructive nature, error handling, or what happens if the record does not exist. The reference to a conditional save plan adds context but is insufficient for full transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, consisting of two sentences that front-load the core action and the data object role. Every word is meaningful, and the structure is efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no output schema and no annotations, the description covers the main action but lacks details on return values, error conditions, or additional behavioral context. The mention of a conditional save plan introduces a concept that is not explained further, leaving some gaps for a comprehensive understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers all three parameters with clear descriptions. The 'data' parameter description notes that it replaces the entire record, aligning with the tool's purpose. Since schema coverage is 100%, the baseline is met, but the description adds minimal extra meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs a full update of an existing data record, overriding the entire record with a provided data object. It distinguishes from the sibling tool 'update_data_record_partial' by emphasizing the full replacement nature.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for full updates but does not explicitly state when to use this tool versus the partial update sibling. No prerequisites or context for the conditional save plan are provided, leaving the agent to infer usage from the name and description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It lacks disclosure of side effects, rate limits, authentication nuances beyond schema, or output behavior. Minimal behavioral detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences: first states purpose, second gives usage guidance. No redundancy, well front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, and description fails to detail return value structure (e.g., array fields). Does not cover error handling or empty results. Incomplete for a tool with one parameter and no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% coverage with detailed description of sessionCredentials. Tool description adds no further parameter semantics beyond referring to output usage, so baseline score applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb+resource: 'Get list of case types that the user can create.' It also distinguishes purpose by linking to create_case, differentiating from sibling get tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says to use returned classID as caseTypeID in create_case, and notes that create_case auto-discovers required fields. Provides clear context for when to use, though no exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates a read-only operation but lacks details on authentication needs, permissions required, or any side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences that convey the purpose without extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a simple retrieval tool; mentions the purpose and domain but could elaborate on return value structure or relationship to sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds no additional parameter semantics beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves a list of participant roles for a specific Pega case, distinguishing it from sibling tools like get_participant or get_participant_role_details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, or any prerequisites or constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must fully disclose behavior. It mentions auto-fetching eTag and cleanup processes but lacks details on side effects (e.g., case state changes, reversibility, required permissions). Insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences: purpose, constraints, then a behavioral note on eTag. No filler, well front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers parameters and constraints but lacks broader context: no explanation of return value, failure modes, or how cleanupProcesses affects assignments. Without annotations, more behavioral context needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline 3. Description adds minimal value: explains eTag auto-fetch and viewType enums, but mostly repeats schema. Adequate but not improved.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'navigate' and resource 'Pega case to its next stage', specifying the primary stage sequence. It distinguishes from siblings like 'change_to_stage' by limiting to next stage only, and explicitly excludes alternate stage and final stage.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description gives clear when-to-use constraints: cannot use when in alternate stage or final stage. It doesn't explicitly name an alternative but context of siblings implies 'change_to_stage' for arbitrary stage changes. Slight gap in explicit alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It states that the tool removes the follower association and ends their subscription. However, it does not disclose side effects (e.g., whether the user is notified, if the action is reversible, or required permissions).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences. The first sentence front-loads the action and primary effect. The second sentence slightly rephrases but adds minimal new information. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple nature of this write operation and the absence of an output schema, the description adequately covers the tool's purpose and immediate effect. It does not address error conditions or prerequisites, but for a straightforward removal action, it is sufficiently complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with detailed descriptions for caseID, followerID, and sessionCredentials. The description adds no additional meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the clear verb 'remove' and specifies the resource 'follower from a case'. It explicitly states the effect of ending notifications and removing the association, which distinguishes it from sibling tools like 'add_case_followers' and 'get_case_followers'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives (e.g., delete_participant for other roles). However, the purpose is clear enough that an agent can infer it is for removing followers specifically, not other case participants.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears full burden. It discloses permanence and permission requirements but does not specify what happens to the document (e.g., is it deleted or just unlinked?), nor side effects, error handling, or idempotency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences: first defines the core purpose, second adds prerequisites. No redundant information. Front-loaded with action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers core action and prerequisites but lacks details on return values, error handling, and what happens if the link doesn't exist. No output schema exacerbates the gap. For a removal tool, basic behavioral completeness is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the description adds only marginal value beyond the schema (reiterating validity and permissions). It does not provide new semantic details for the parameters beyond what is already in the input schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description uses specific verb 'remove' and resource 'document linked to a case', clearly distinguishing from sibling tools like delete_attachment or delete_case. It explicitly states the operation removes the link, not the document itself.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description mentions prerequisites (valid IDs, permissions) but does not provide explicit when-to-use or when-not-to-use guidance compared to alternatives. No mention of alternative tools for similar tasks (e.g., update_attachment or delete_case).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool reads ancestor hierarchy and returns basic info with links, which is adequate for a read operation. However, it does not mention any potential side effects or authorization constraints (though these are implied in the input schema).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loading the purpose and adding specific detail in the second sentence. No superfluous words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (get ancestor hierarchy) and the description explains the return content (basic info + HATEOAS links). Without an output schema, this is sufficient for an agent to understand the result. The input schema covers parameters completely.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema coverage is 100% with detailed descriptions for both parameters. The description adds little beyond the schema (e.g., 'for the case ID passed in'). Baseline 3 is appropriate since the schema already covers the meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves ancestor case hierarchy for a specific case, specifying it returns parent-child relationships and basic case info with HATEOAS links. This differentiates it from siblings like get_case_descendants and get_related_cases.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving hierarchical ancestors but does not explicitly state when to use vs alternatives or provide exclusion criteria. No guidance on prerequisites or context compared to other hierarchy tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It describes the return data and is functional, but does not explicitly state that the tool is read-only, or disclose auth requirements, rate limits, or potential exceptions like empty lists. Adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the action and result. No unnecessary words, every part contributes to understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read operation with 2 parameters (one nested) and no output schema, the description adequately covers the purpose and return content. It could mention that the list may be empty or that sessionCredentials are optional, but the schema already covers that. Overall, fairly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description does not add extra meaning beyond what the schema provides for the parameters; it focuses on return data. No additional parameter-specific context is given.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves all participants for a specific Pega case and specifies the return includes roles, permissions, and contact information. This distinguishes it from sibling tools like get_participant (single participant) or get_participant_role_details (roles only).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for case access management but does not explicitly state when to use this tool versus alternatives like get_participant or create_case_participant. No exclusions or when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It adds the auto-expiry behavior and multiple input methods, but does not disclose authentication requirements, return values, or side effects. The schema descriptions cover some behaviors, but the description itself is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, front-loaded with purpose and key behavioral detail, with no wasted words. It earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (8 params, nested objects, no output schema), the description lacks return value information, error handling, and authentication context. It provides the auto-expiry detail but is insufficient for full understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description does not add significant meaning beyond the schema; the mention of 'multiple input methods' is already evident from the parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool uploads a file as a temporary attachment that can later be linked to cases, with an explicit verb and resource. It distinguishes from sibling tools like add_case_attachments by noting the temporary nature and auto-expiry.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context by stating the attachment is temporary and expires after 2 hours if not linked, implying it should be used for uploads intended for later linking. However, it does not explicitly name alternatives or state when not to use it, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It mentions creating a participant and adding users to case access control. But it lacks details on prerequisites (e.g., required permissions), side effects (e.g., triggering workflows), or whether the operation is reversible. The eTag auto-fetch is a helpful behavioral detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is relatively concise with four sentences, each adding unique information. It is front-loaded with the primary purpose. While more details could be added, it does not contain unnecessary fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (7 parameters, nested objects, no output schema), the description covers the core functionality, eTag behavior, and access control implication. It lacks error handling or prerequisites (e.g., case ID format) but is reasonably complete for agent invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, but the description adds significant value: for eTag it explains auto-fetch and performance benefit; for content it specifies the Data-Party schema; for participantRoleID it links to permissions; and for pageInstructions and sessionCredentials it provides detailed examples and modes. This exceeds what the schema alone provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool creates a new participant in a Pega case with a specified role and participant information. It distinguishes from siblings like add_case_followers, update_participant, and delete_participant by focusing on creation and access control.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides some usage guidance, such as the auto-fetch behavior for eTag and the option to provide it for faster execution. However, it does not explicitly contrast with alternative tools like add_case_followers or update_participant, leaving room for confusion on when to use each.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses key behavioral traits: validation of attachmentID, access check, and different return types. This is sufficient for a read operation with no side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, each adding value: purpose, return types, validation/access check. No unnecessary words. Well-structured and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so description should explain return values. It does list return types but doesn't specify conditions for each (e.g., when is URL vs Base64). Also no error handling info. Adequate but has gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description does not add significant parameter details beyond what the schema provides (e.g., attachmentID format, sessionCredentials modes). The schema already has detailed descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Get the attachment content based on the attachmentID.' It specifies the different content types (Base64, URL, HTML) based on attachment type, distinguishing it from sibling tools like get_attachment_categories or delete_attachment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains what the tool does but does not explicitly guide when to use it versus alternatives. It implies usage for retrieving attachment content, but does not mention when to use other tools like get_case_attachments for listing attachments.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. While it indicates a read operation, it fails to disclose any behavioral traits such as side effects, required permissions, or data freshness. This is insufficient for an agent to fully understand the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences, front-loaded with purpose and usage. No wasted words, each sentence adds clear value and is well structured for quick parsing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description provides a good overview of output content but omits details about the viewType parameter, which controls UI resource inclusion. Additionally, the complex sessionCredentials object is not explained. Given the no output schema, more context on return structure would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description does not add meaningful extra detail beyond the schema; it mentions returned content but not parameter-specific guidance. Thus it meets the baseline without adding value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves comprehensive case information including status, stage, assignments, and available actions. It distinguishes itself from siblings by specifically mentioning get_assignment for assignments, making its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance: use after workflow completion or for case overview, not immediately after create_case (redundant), and for assignments use get_assignment. This clearly delineates when and when not to use the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description effectively discloses key behaviors: automatic eTag fetching, supported operations (recalculating fields/whens, merging content, applying page instructions), validation of IDs, and returning updated values. It could mention auth requirements or side effects but is fairly transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at 6 sentences, front-loaded with the core purpose. Each sentence adds value with minimal redundancy, though some details (e.g., API validation) could be considered verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (7 parameters, nested objects, no output schema), the description covers main features, eTag handling, and return type. It lacks specifics on error conditions and exact response format but provides a solid overview.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description summarizes parameters (eTag auto-fetch, content merge, pageInstructions) but does not add significant new meaning beyond the schema's definitions. It provides a helpful overview but no extra detail.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool recalculates calculated fields and whens for the current assignment action form, specifying the resource (assignment action form) and action (recalculate). It distinguishes from sibling recalculate_case_action_fields by scope (assignment vs case).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for assignment action forms but does not explicitly state when to use or when not to use this tool vs alternatives like recalculate_case_action_fields. No exclusions or alternative recommendations are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description discloses key behaviors: partial update leaves other fields unchanged and not supported for PEGA System of records. Could mention side effects or prerequisites but sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, no extraneous information, front-loaded with the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequately describes partial update behavior and limitation, but lacks output schema or return value description, which is a gap for an update tool with no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% coverage with detailed parameter descriptions; the tool description adds marginal context (conditional save plan, PEGA limitation) but no parameter-specific semantics beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it partially updates a data record based on a conditional save plan for a savable Data Page, distinguishing it from full updates.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Implied usage via sibling tool 'update_data_record_full' for partial updates, but no explicit when-to-use or when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses atomicity (all-or-nothing) and hints at the 2-hour expiry of temporary attachments in the schema. However, it doesn't cover error handling, authentication details, idempotency, or required permissions. More behavioral context would be helpful.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences, front-loaded with the purpose and then key behavioral detail (atomicity). Every word earns its place. No redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (nested objects, no output schema), the description is fairly complete. It covers the main functionality and atomicity. The parameter descriptions fill in details like temporary ID expiry. Could mention return value, but not critical.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed parameter descriptions. The main description adds complementary context (e.g., using IDs from upload_attachment, types of attachments). Since coverage is high, baseline is 3, and the description adds marginal value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool attaches files and/or URLs to a Pega case, regardless of context or stage. It distinguishes from siblings like upload_attachment (which uploads temporary files) and get/update/delete attachment tools. The verb 'attach' and resource 'case attachments' are specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use: for attaching temporary files (via IDs from upload_attachment) or URLs directly. It mentions atomicity ('if any attachment fails, no attachments are added'). It could be more explicit about when not to use, but provides clear context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It mentions storing the authentication token in session, which is key behavior. It does not discuss side effects like overwriting existing sessions or rate limits; however, for an auth tool, this is adequate but not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, front-loaded with the primary action (authenticate), and no unnecessary words. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description covers the main behavior and usage context. It could mention error handling or session lifetime, but overall it is complete for a simple authentication tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description does not add parameter-specific details beyond the schema, but the schema already provides good descriptions. Therefore, the description adds no extra value to parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool authenticates with Pega Infinity using OAuth2 client credentials or direct access token, and stores the token in session. It distinguishes from sibling tools (which perform CRUD operations) by being a setup tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
It says 'should be used before making API calls when you want to explicitly manage authentication,' providing clear context for use. It does not mention alternatives or when not to use it, but the guidance is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description adds some behavioral context (sync/async per platform), but lacks details on error handling, partial failures, or idempotency, leaving gaps for a bulk mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences: purpose, platform behavior, and scope limitation. No wasted words, well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a bulk action tool: covers main behavioral distinctions and scope, but lacks details on return values and error handling, which are not compensated by output schema or annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed parameter descriptions; the tool description adds marginal high-level context that doesn't significantly enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it performs case actions on multiple cases via PATCH endpoint, and specifies the type of actions supported (case-wide, not assignment-level), distinguishing from single-case and other bulk tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly excludes assignment-level actions, guiding when not to use, but does not name explicit alternative tools like perform_case_action or get_case_type_bulk_action.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It does not disclose any behavioral traits beyond the basic 'get' operation, such as idempotency, rate limits, required permissions, or data retrieval limitations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The main description is two concise sentences. Parameter descriptions are detailed but not verbose, each sentence adding necessary information. Structure is clean and focused.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 parameters, no output schema, and a complex nested sessionCredentials object, the description is thorough. It explains purpose, parameters with examples and cross-references, and authentication modes, making it complete for invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds significant value beyond the schema by providing examples, explaining case-sensitivity and format for actionID, and detailing authentication modes for sessionCredentials. This greatly aids correct parameter selection.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves bulk action metadata for a specific case type and action ID, using a specific verb and resource. It is easily distinguishable from siblings like get_case_type_action (single action) and perform_bulk_action (execution).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives. It provides a usage hint for the actionID parameter ('Use get_case_types to discover...'), but lacks general guidance on context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that navigation can set optional content and page instructions, implying potential side effects. However, it does not explicitly state whether the operation is read-only or destructive, or mention any safety or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose and includes necessary details. While it is somewhat lengthy, each sentence serves a purpose, such as explaining step ID discovery and viewType behavior. Minor redundancy could be trimmed.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (8 parameters, nested objects, no output schema), the description covers usage and parameter semantics but does not describe the return structure beyond 'navigation breadcrumb' and 'step details'. Missing error handling or expected behavior for invalid steps. Adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds significant meaning beyond schema field names. It explains step ID formats, eTag for performance, content mapping, page instructions for embedded pages, attachments, viewType options, and session credentials. This helps agents understand each parameter's role.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action: 'Jump to the specified step within an assignment's navigation flow and return the details of the step.' It distinguishes from progressive sequential navigation and mentions additional navigation breadcrumb data. The purpose is specific and actionable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use (multi-step assignments, screen flows, complex processes) and how to discover valid step IDs (via get_assignment, breadcrumb, process definition). It does not explicitly state when not to use, but the guidance is clear and helpful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It outlines the process (pre-processing, data merging, validation), notes action ID case sensitivity, eTag behavior, and attachment handling. It is transparent about the API workflow, though it does not detail potential side effects or authentication requirements beyond the sessionCredentials parameter.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured, starting with purpose then detailing parameters and behavior. While moderately long, each sentence adds value and the structure is logical. Minor improvement would be to tighten some explanations.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description covers the tool's functionality well, including parameter nuances, workflow steps, and authentication via sessionCredentials. It does not explain the return value format or prerequisites, but for a tool with 10 parameters and nested objects, it is sufficiently complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds significant extra value for many parameters: eTag (auto-fetch vs manual), actionID (case sensitivity, source), attachments (usage guidance), pageInstructions (examples, instruction types), content (example), and others. This greatly enhances understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (perform) and resource (case action) with 'Perform an action on a Pega case, updating case data and progressing the workflow.' It distinguishes from sibling tools like perform_assignment_action by focusing on case actions, but could explicitly contrast to avoid ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains parameter usage (e.g., eTag auto-fetch) but does not provide explicit guidance on when to use this tool versus alternatives like perform_assignment_action. Some context is given, but no exclusions or situational advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses validation of IDs, processing of calculations, merging content, and page instructions. It does not contradict annotations. However, it omits potential side effects like persistence or locking, but overall provides good behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is somewhat lengthy but each sentence contributes value. It is well-structured with the main purpose front-loaded. Minor verbosity but overall efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema is provided, and the description only vaguely mentions returning updated field values/states. For a complex tool with nested parameters, more detail on return structure would improve completeness. Sibling tools further highlight this gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, but the description adds meaningful context beyond the schema. It explains the purpose of each parameter (e.g., pageInstructions for embedded pages with examples), enhancing understanding for agents.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool recalculates calculated fields and whens for the current case action form, specifying a specific verb ('recalculate') and resource ('case action fields'). It distinguishes from siblings like recalculate_assignment_fields by focusing on case action context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the process and auto-fetching behavior but does not explicitly state when to use this tool over alternatives or provide exclusions. Implicitly it's for recalculating after user input, but lacks clear guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of transparency. It discloses key behavioral traits: validation of case and action IDs, auto-fetching of eTag if missing, execution of Data Transforms, and support for modal table operations. It also notes that field values override preprocessing Data Transforms, indicating mutability. However, it does not mention error behavior, idempotency, or rate limits, which are minor gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single paragraph of about 4-5 sentences, concise and front-loaded with the main purpose. While it packs a lot of information, it remains readable. It could benefit from more structured formatting (e.g., bullet points for features), but it is not overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (13 parameters, no output schema, nested objects), the description provides a good overview but lacks specificity about the response format. It only says 'returns information about fields affected by the refresh action,' which is vague. It does not cover error scenarios or guarantee of completeness, leaving some gaps for a complex operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds value beyond the schema by explaining high-level concepts like 'form refresh settings configured in Flow Action rules' and 'generative AI form filling', which contextualize parameters like 'refreshFor' and 'fillFormWithAI'. It does not repeat schema descriptions but enriches understanding of the tool's operation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Refresh case action form data with updated values after property changes, execute Data Transforms, and handle table row operations in modals.' It identifies the specific resource (case action form data) and the primary verbs (refresh, execute, handle). While there is a sibling tool 'refresh_assignment_action', the description distinguishes this by focusing on case actions and mentioning Pega Infinity '25 features, making the purpose specific and distinct.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides context for when to use the tool (after property changes to refresh form) but does not explicitly state when not to use it or mention alternatives. For example, it does not differentiate from 'refresh_assignment_action' or 'perform_case_action' which might be similar. The guidelines are implied rather than explicit, leaving room for confusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description bears the burden. It discloses optimistic locking via eTag, partial updates (only provided properties changed), and return of updated details with UI resources. However, it lacks details on side effects, concurrency guarantees, or access requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, each serving a distinct purpose: purpose, eTag behavior, updateable fields, and requirement/return. No filler, well front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 7 parameters with nested objects and no output schema, the description covers core behavior (update, eTag, partial updates, pageInstructions, return with UI). It omits error handling and response structure details, but remains fairly complete for a mutation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds value beyond schema: explains eTag auto-fetch, partial update behavior for content, and the purpose of pageInstructions usage. This elevates it above the baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses specific verb 'Update' and resource 'participant details in a Pega case', clearly distinguishing it from sibling tools like create_case_participant and delete_participant.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the eTag auto-fetch behavior for convenience, but does not provide explicit when-to-use vs. alternatives or mention restrictions like required permissions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses authentication, privilege validation, case history update, and behavior for multi-linked attachments. Without annotations, it adequately covers behavioral traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Four concise sentences with no waste, front-loaded with purpose. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers behavior and authentication but lacks mention of return value or error states, which is a gap given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed descriptions. The tool description adds little beyond schema, meeting the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Remove the specified attachment from a case' with a specific verb and resource. It distinguishes from sibling tools like upload_attachment and update_attachment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides context on who can delete and the effect on linked attachments, but lacks explicit when-not-to-use or alternatives. Clear enough given no sibling delete tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description covers max results limit and hasMoreResults field, but does not explicitly state read-only nature or authentication implications beyond parameter descriptions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with numbered examples and clear sections. Slightly verbose due to many examples, but justified given the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema; description mentions hasMoreResults but does not specify the exact return structure (e.g., count field name, type). Lacks details on response format for success/error.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds significant value with extensive examples for all query configurations, covering aggregation, filter, calculation, and paging use cases.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves a total count without fetching data, and distinguishes from get_list_data_view. Examples reinforce purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly mentions use cases like pagination planning and performance optimization. Implicitly contrasts with get_list_data_view via 'same comprehensive query capabilities,' but does not explicitly state when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses key behavioral traits: supported use cases, filter comparators, aggregation functions, paging limitations, extended timeout conditions, and authentication modes. It also notes constraints like distinctResultsOnly cannot be used with aggregation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with numbered use cases, tables for comparators, and clear examples. It is somewhat lengthy but every section adds value. It front-loads the purpose and provides progressive detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (6 parameters, nested objects, no output schema), the description is comprehensive. It covers all use cases, explains each parameter, and provides examples. However, it does not explicitly describe the return format or structure of the response, which would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds significant value by providing extensive examples, enumerating supported comparators and aggregation functions, and explaining parameter interactions (e.g., paging modes, authentication options). This goes beyond the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Retrieve list type data view with advanced querying capabilities.' It then enumerates four distinct use cases with concrete examples, making it easy for an agent to understand exactly what the tool does and how it differs from siblings like get_data_view_count or get_data_view_metadata.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
While the description provides detailed examples and use cases, it does not explicitly guide when to use this tool versus alternatives like get_data_view_count for counts or other data retrieval tools. Usage is implied but not contrasted with siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. Discloses auto-fetch of eTag, default actionID, and local action scope, but does not address side effects, error conditions, or reversibility.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, each adding unique value: purpose, version distinction, auto-fetch behavior, default action. No redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 7 parameters including nested objects and no output schema, description covers core usage but lacks details on return format, error handling, or success indicators. Adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters. Description adds value by explaining eTag auto-fetch, default actionID, and that content can be empty for action-only updates. Adds context beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb 'Update' and resource 'Pega case', with explicit differentiation from V2 API and sibling tools like perform_case_action. 'Modifying case properties' further specifies scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states 'V1 EXCLUSIVE' and directs V2 users to perform_case_action. Provides alternative guidance but lacks explicit when-not-to-use scenarios besides version restriction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the requirement for an eTag for optimistic locking, automatic fetching if omitted, and the return of success or error details. This provides adequate transparency about the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: two sentences that are front-loaded with the core action, followed by essential details. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 4 parameters including a nested sessionCredentials object, no output schema, and many siblings, the description adequately covers the core behavior, parameter usage, and outcomes. It could mention the response format explicitly, but the mention of 'success confirmation or detailed error information' is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds some context (e.g., auto-fetch eTag, seamless operation) but does not significantly enhance understanding beyond what the schema already provides for each parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (delete a participant), the target (Pega case by case ID and participant ID), and explicitly distinguishes from siblings like create_case_participant and update_participant by focusing on deletion with optimistic locking via eTag.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool (to delete a participant from a case) and highlights convenience features like automatic eTag fetching. It does not explicitly mention when not to use it or compare with alternatives, but the purpose is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It mentions 'Pessimistic locking may apply' and explains the eTag requirement, which are useful behavioral traits. However, it does not explicitly confirm that the operation is read-only.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, front-loaded with the main purpose, and each sentence adds value without unnecessary detail. It is efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 4 parameters, nested objects, and no output schema, the description adequately covers the return values ('form structure, action IDs, and eTag') and explains the viewType parameter. It could elaborate slightly on pageName but is generally complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds some context (e.g., assignmentID format example, explanation of 'required' field markers), but most parameter details are already in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get assignment details including form fields, required fields, available actions, and eTag.' It also specifies the usage context 'BETWEEN case creation and action performance,' which distinguishes it from sibling tools like get_assignment_action and perform_assignment_action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates the tool is used between case creation and action performance, providing context. However, it does not explicitly state when not to use it or name alternative tools such as get_assignment_action for action-specific details.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description fully bears the burden of behavioral disclosure. It reveals that the API uses the class name from caseID to fetch categories, filters by type, and returns only configured categories. It also mentions permission details (view, create, edit, delete). No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is reasonably concise and front-loaded with the core purpose. However, it includes some redundant phrasing (e.g., 'useful for understanding') that could be trimmed. Still, it is informative without being overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given there is no output schema, the description adequately explains return values (category metadata with permissions). It covers filtering logic and parameter dependencies. The tool is straightforward, and the description provides sufficient context for an agent to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but the description adds meaningful context: e.g., explaining that the API derives class name from caseID, the case-insensitive filtering by type, and the default value for type. For sessionCredentials, it outlines authentication modes. This adds value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves attachment categories for a Pega case, filtered by type (File or URL), and returns metadata including permissions. It distinguishes itself from sibling tools like get_attachment and get_case_attachments which focus on attachments themselves rather than categories.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool (to understand available attachment categories and user permissions) but does not explicitly state when not to use it or compare it to alternatives. However, it provides enough context for most use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description bears the full disclosure burden. It details the metadata returned (file details, URLs, actions) and explains optional thumbnail retrieval with base64 encoding. It could mention read-only nature, but overall transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences efficiently cover purpose and key details. No redundant information, front-loaded with the essential action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description provides adequate context: return content, category filtering, thumbnail option. It does not explain sessionCredentials in description (covered by schema), nor address pagination, but is largely complete for a list-retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% description coverage. The description adds value by elaborating on the thumbnail parameter (e.g., file types, base64) beyond the schema. For caseID, it does not add much, but overall enhances understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Get a comprehensive list of all attachments associated with a specific Pega case.' It specifies the resource (attachments for a case) and distinguishes from siblings like 'get_attachment' (single attachment) and 'add_case_attachments'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions that only attachments from selected categories are returned, but does not explicitly compare to alternatives like 'get_attachment' or provide when-to-use guidance. Usage context is implied but not clearly outlined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden and discloses recursive looping, return of assignments/actions, and access restrictions. However, it does not mention performance implications or error cases.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with front-loaded purpose and subsequent detail. No redundant information, each sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, behavior, and access nuances. Lacks details on output format and performance, but is reasonable given the tool's complexity and lack of output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed parameter descriptions. The tool description adds no additional meaning beyond what the schema already provides, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'get' and the resource 'descendants of a case instance', and specifies the recursive behavior returning assignments and actions, distinguishing it from siblings like get_case_ancestors.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on access limitations (limited info if unauthorized) which helps in deciding when to use, but does not explicitly mention alternatives or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses creation of initial assignment, return values (caseID, assignmentID, eTag), and mentions auto-discovery. However, it does not discuss authorization needs, rate limits, error conditions, or side effects beyond creation. Adequate but not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single paragraph that front-loads the purpose, then logically flows to results, guidance on parameters, and next steps. Every sentence adds value with no redundancy or fluff. Efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (9 parameters, nested objects) and lack of output schema, the description covers purpose, key parameters, return values, and workflow. It lacks explicit error handling or prerequisites, but the guidance on content and next steps is thorough enough for an AI agent to use effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the description adds significant meaning beyond the schema. It explains when to use empty content, provides an example for pageInstructions, details authentication modes for sessionCredentials, and clarifies the role of return values. This goes well beyond the schema definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Create' and resource 'a new Pega case', and positions it as 'the FIRST step in case workflows'. This distinguishes it from sibling tools like get_case or update_case, providing clear purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use this tool (as first step), provides guidance on content (many case types accept empty content, auto-discovery for required fields), and states next steps (use get_assignment). It lacks explicit when-not or comparisons to alternatives, but the workflow context is strong.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but description discloses behavioral traits: optimistic locking via eTag, auto-fetch if omitted, returns breadcrumb info depending on viewType, and ability to set content/attachments during navigation. Could mention potential side effects like data saving, but overall sufficiently transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is well-structured with front-loaded purpose and subsequent details. At five sentences, it is slightly verbose but every sentence adds essential information. No redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, 7 parameters, nested objects, and no output schema, the description covers eTag behavior, navigation mechanism, modification capabilities, and prerequisites. Missing return format details (only mentions breadcrumb under uiResources) but overall comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds value beyond schema: explains eTag auto-fetch and optimization, clarifies that content/attachments/pageInstructions are for modification during navigation, and defines viewType impact on UI resources. Schema descriptions are present but description enhances utility.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool navigates to the previous step in screen flows or multi-step forms, distinguishing it from siblings like jump_to_step. It also explains automatic eTag fetching for seamless operation, making the purpose specific and actionable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides context on when eTag auto-fetch is used and mentions optimization, but does not explicitly state when not to use this tool or compare with alternatives like jump_to_step. Still, the usage context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses key behavioral traits: required field validations are ignored, only server-side validations are performed, eTag auto-fetches if omitted, and the tool is available for specific action types. Since no annotations are provided, the description carries full burden and covers most important behaviors, though it does not mention concurrency or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, information-dense paragraph with no wasted sentences. The first sentence immediately states the core purpose. While it could be more structured with bullet points, it remains concise and readable. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (8 parameters, nested objects, no output schema), the description covers purpose, usage context, validation behavior, eTag handling, and supported action types. It lacks explicit return value description, but the focus is on the save action itself. Overall, it is sufficiently complete for an AI agent to understand how to use the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage, the baseline is 3. The description adds meaningful context beyond schema: it clarifies that only fields part of the assignment action's view can be saved, gives detailed examples for pageInstructions and attachments, and explains the eTag auto-fetch behavior. This enhances understanding beyond the parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool saves assignment action form data without executing the action, implementing 'Save for later' functionality. It specifies the target resource (assignment action form data) and the verb (save), and distinguishes it from sibling tools like perform_assignment_action by emphasizing it does not execute.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use the tool: for saving form data in progress for Connector actions like Collect info steps, screen flow assignments, and customized approval steps. It implicitly contrasts with perform_assignment_action. However, it does not explicitly state when not to use it or list alternative tools for specific scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, but the description discloses a key behavioral trait: 'without exposing secrets.' It implies a read-only diagnostic operation, which is sufficient for this simple tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, both essential and front-loaded. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple diagnostic tool with no parameters or output schema, the description is complete: it explains purpose, usage context, and a behavioral constraint. Missing details about specific output format are acceptable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has zero parameters, so schema coverage is 100%. The description adds no parameter details because none exist, which is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Diagnose Pega configuration and environment variables to troubleshoot connection issues.' It distinguishes from siblings like ping_pega_service by focusing on configuration details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit context: 'to troubleshoot connection issues.' While it doesn't mention when not to use it or list alternatives, the context is clear and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description covers key behaviors: V1-only, limit of 500, ordering, authentication, and privilege requirement. It could mention if pagination is supported or if the operation is read-only, but the constraints are well communicated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with key information (purpose, constraints, privilege), no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one parameter (credentials) and no output schema, the description adequately covers core functionality and constraints. Lacks details on error handling or output format, but sufficient for a simple retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single parameter, so the schema already documents credentials thoroughly. The description adds no additional parameter meaning beyond what's in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool retrieves all cases for the authenticated user, with constraints (V1 exclusive, max 500, oldest to newest), and distinguishes from siblings by directing V2 users to Data Views.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly tells when to use (V1) and when not to use (V2), naming the alternative (Data Views), and mentions the required privilege (pxGetCases).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description mentions 'lightweight API call' and 'using existing authentication', but does not detail response format or error handling. Still adequately transparent for a connectivity test.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences: first defines purpose, second gives usage guidance. No redundant words, front-loaded with key information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and the presence of sibling tools, the description sufficiently covers purpose, usage context, and prerequisite. Could mention expected response (e.g., success/failure indicator) for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 100% description coverage for the nested sessionCredentials parameter. The tool description adds no additional meaning beyond what the schema already provides. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the verb 'Test connectivity and system availability' and resource 'Pega Infinity server'. Distinguishes from sibling 'authenticate_pega' by specifying authentication prerequisites.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs to use 'authenticate_pega' first if authentication is needed, providing clear when-to-use vs. alternative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully carries the burden. It discloses limitations (only updates title/category, not filename/URL) and an authorization check (verifies user access to category). No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences, front-loaded with purpose, then limitations, then security. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, limitations, and security check. Missing description of return value or success indication, but given that there is no output schema, this is a minor gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema descriptions cover 100% of parameters, so baseline is 3. The description adds minimal extra parameter meaning beyond stating what fields are updated, which is already implied by the parameter names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool updates the name and category of an existing attachment, using specific verbs and resource. Siblings like add_case_attachments, delete_attachment, and upload_attachment have different purposes, so this tool is well-distinguished.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear context on what the tool updates and does not update (filename/URL). However, it does not explicitly state when to use this tool versus alternatives like add_case_attachments or upload_attachment.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description adds important behavioral context: 'If the case type uses pessimistic locking and the client uses Constellation, this request may lock the case.' It also specifies that it retrieves details for ONE specific action. However, it does not explicitly state that the tool is read-only or idempotent, which would further improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise (5 sentences) with no wasted words. It is front-loaded with purpose and usage, then covers parameters efficiently. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, yet the description only mentions 'including UI metadata and preprocessing execution' without detailing the response structure. For a tool retrieving detailed action info, it would benefit from outlining what fields or data are returned (e.g., similar to get_assignment). It is adequate but incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description significantly enhances parameter understanding: explains actionID case sensitivity and relation to display names, gives example for assignmentID, clarifies viewType options, and describes sessionCredentials authentication modes. This goes well beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get detailed information about a specific action that can be performed on an assignment.' It uses a specific verb ('Get') and identifies the resource ('assignment action'). It also differentiates from sibling tools by outlining the typical workflow where get_assignment is preferred.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit guidance: 'Often optional - most workflows use: get_assignment (all actions + eTag) → perform_assignment_action. Use this when you need action-specific details.' It also instructs to use get_assignment to find the correct action ID, setting clear usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key behaviors: auto-fetches eTag if not provided, returns updated case with either nextAssignmentInfo (more work) or confirmationNote (workflow complete), and explains local vs connector action progression. Since no annotations exist, description fully covers behavioral aspects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is comprehensive yet well-structured. It front-loads the purpose and then details parameters. While relatively long, every sentence adds value and avoids redundancy. Could be slightly more concise, but still efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (9 parameters with nested objects, no output schema), the description covers usage, parameter behavior, return outcomes, and edge cases (eTag auto-fetch, attachment vs pageInstructions). It explains the two possible results (nextAssignmentInfo or confirmationNote) and handles all necessary context for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema coverage, baseline is 3 but description adds significant value: explains assignmentID format with examples, actionID case-sensitivity and ID vs name, eTag optionality, content requirement, pageInstructions usage with examples, and a crucial clarification about attachments (not for linking temporary uploads). Greatly enhances understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool performs an assignment action to submit work and progress workflow, specifying it's the final step after filling required fields. It distinguishes itself from sibling tools like get_assignment by being the action execution step.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says to use after all required fields are filled and notes auto-fetch of eTag. Provides context for when it's appropriate (final step) but does not explicitly list when not to use or alternative tools like save_assignment_action.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It clearly explains synchronous vs asynchronous behavior, action ID case sensitivity and space rules, and explicitly lists unsupported action types. Does not describe return value or error behavior, but given complexity, this is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is lengthy but well-structured with clear sections. It is front-loaded with main purpose and behavior. Every sentence adds value, but could be slightly more concise without losing information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (7 parameters, nested objects, async/sync modes, platform differences), the description covers all aspects including limitations and best practices. No output schema, but behavior is sufficiently explained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, but description adds substantial value: explains actionID case sensitivity and example, integration with get_case; explains runningMode limitations; provides detailed pageInstructions with examples; describes sessionCredentials auth modes. This goes beyond schema to enhance understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs a case action on multiple cases simultaneously. It uses specific verb 'Perform' and resource 'case action on multiple cases', and distinguishes from sibling tools like 'perform_case_action' (single case) and 'bulk_cases_patch' (different operation).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use (bulk operation on multiple cases) and when not (assignment-level actions like Transfer are not supported). Provides context on synchronous vs asynchronous behavior for Infinity vs Launchpad. Also directs to use get_case to find correct action ID.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses validation of IDs, view data retrieval, execution of Data Transforms, and that field values overwrite preprocessing. Notes non-visible fields cannot be set and eTag behavior. Lacks explicit mention of mutation or auth needs, but overall transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single paragraph, well-structured: purpose first, then details, then usage. Each sentence adds value. Could be broken into multiple paragraphs for readability, but concise enough.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 10 parameters, nested objects, no output schema, description is remarkably complete. Covers all parameters, usage scenarios, eTag behavior, limitations (non-visible fields). Missing return format but not expected without output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline 3. Description adds significant value: actionID case sensitivity and ID retrieval method, refreshFor trigger, operation enum context, interestPage and interestPageActionID explained, content overwrite behavior, pageInstructions with examples. Goes beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Refresh assignment action form data' and distinguishes from 'perform_assignment_action' for final submission. It lists specific capabilities: execute Data Transforms, handle table row operations, and progressive filling. This differentiates it from siblings like get_assignment_action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states 'Use refresh for partial updates with validation; use perform_assignment_action for final submission' and 'OPTIONAL tool for progressive filling (multiple calls OK)'. Also mentions eTag consistency across refreshes, providing clear when-to-use and when-not-to-use guidance with sibling reference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![pega-dx-mcp MCP server](https://glama.ai/mcp/servers/marco-looy/pega-dx-mcp/badges/card.svg)](https://glama.ai/mcp/servers/marco-looy/pega-dx-mcp)

Score Badge

Copy to your README.md:

[![pega-dx-mcp MCP server](https://glama.ai/mcp/servers/marco-looy/pega-dx-mcp/badges/score.svg)](https://glama.ai/mcp/servers/marco-looy/pega-dx-mcp)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/marco-looy/pega-dx-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server