agent-pool-mcp

by rnd-pro

Overview Schema Related Servers Score Discussions

JavaScript

Local

Server Quality Checklist

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

Latest release: v1.7.3
Disambiguation4/5
Most tools have distinct purposes, but delegate_task and delegate_task_readonly are very similar, differing only in intent signal. The large number of tools (42) introduces some risk of confusion, though descriptions are clear.
Naming Consistency5/5
Tool names consistently follow a verb_noun pattern (e.g., get_pipeline_status, create_skill, list_groups). Only minor deviations like bounce_back, but overall the pattern is clear and predictable.
Tool Count3/5
With 42 tools, the set is quite large for a single server. While each tool serves a specific purpose, the count exceeds the typical well-scoped range (3-15). It may overwhelm agents, but the complexity of the domain partially justifies the number.
Completeness4/5
The tool surface covers core workflows: delegation, pipelines, scheduling, groups, skills, workflows, messaging, and file tracking. Minor gaps exist, such as missing update/delete operations for pipelines and groups, but the set is generally comprehensive.
Average 3.6/5 across 42 of 42 tools scored. Lowest: 2.8/5.
See the Tool Scores section below for per-tool breakdowns.
- 0 of 2 community issues answered or closed in the last 6 months
- 42 commits in the last 12 weeks
- No stable releases found
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI status not available
This repository is licensed under MIT License.
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

Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only says 'create' without disclosing side effects, destructive potential, or any behavioral traits beyond the basic action.
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 efficient sentence, front-loaded. However, could benefit from additional context while remaining concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, no annotations, no description of return values, error handling, or preconditions. Incomplete for a meaningful 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%, so baseline is 3. Description adds no extra meaning beyond schema, but does not detract.
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 states exact action ('Create a pipeline definition') and distinguishes from sibling tools like 'run_pipeline' or 'list_pipelines'.
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, prerequisites, or how it differs from alternatives like 'delegate_task' or 'create_skill'.
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. Only states 'start executing', which implies mutation but lacks details on side effects (e.g., runs asynchronously, returns a run ID), required permissions, or what happens to ongoing executions.
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?
Single sentence is concise but adds minimal value beyond the tool name. It is not overly verbose, but could include more useful context without becoming lengthy.
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 no annotations, leaving many gaps: no indication of return value, execution model (sync/async), or state requirements. Description fails to provide a complete mental model for 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 descriptions for all three parameters, so baseline is 3. Description adds no extra meaning beyond 'start executing' but does not need to compensate given schema already documents parameters adequately.
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 uses verb 'start' and resource 'pipeline execution', which clearly indicates the tool initiates a pipeline. It is not a tautology and distinguishes from siblings like 'cancel_pipeline' or 'get_pipeline_status' by focusing on starting rather than monitoring or stopping.
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 'get_pipeline_status' or 'cancel_pipeline'. Does not specify prerequisites like pipeline existence or state, nor 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?
No annotations are provided, so the description must fully disclose behavior. It mentions the storage location but does not specify whether updates overwrite or merge, any permissions needed, or potential side effects like overwriting existing skills.
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 and front-loaded with the purpose and location. Single sentence with no extraneous words.
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?
For a creation tool with 6 parameters and no output schema, the description should explain expected output, such as confirmation or the created skill's details. This is missing, leaving the agent under-informed.
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 extra meaning beyond the parameter descriptions. Baseline 3 applies; no additional enrichment is provided.
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 creates or updates a CLI skill under a specific path, using a specific verb and resource. However, it does not differentiate from related tools like install_skill or delete_skill.
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 create vs update, or how this compares to sibling tools like install_skill or delete_skill. The description lacks context for tool 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?
Without annotations, the description lacks any behavioral disclosure such as read-only nature, side effects, or return format. It does not indicate that the tool is safe or non-destructive, leaving the agent uninformed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness2/5
Is the description appropriately sized, front-loaded, and free of redundancy?
At only three words, the description is under-specified rather than efficiently concise. It omits critical information about scope, output, and behavior, making it insufficient for an agent to use correctly.
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?
The description does not explain what information is returned for each pipeline definition or the default output format. Given the absence of an output schema, this gap makes the description incomplete for the tool's complexity.
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 clear descriptions, so the tool description does not need to add further meaning. The description adds no value beyond the schema, earning 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 verb 'list' and the resource 'all pipeline definitions,' making the tool's purpose immediately understandable. It differentiates from siblings like 'get_pipeline_status' which targets specific pipelines, and 'create_pipeline' which creates new ones.
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. For example, there is no mention that this is for overview purposes or that 'get_pipeline_status' should be used for a single pipeline's details.
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 carries full burden. It implies read-only behavior but does not disclose return format (e.g., names, paths, metadata) or whether 'local' refers to agent filesystem or app storage.
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 is concise and front-loaded. Could benefit from additional details, but structure is efficient for a basic tool.
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 exists, yet description omits return value information. The tool is simple, but the lack of output details reduces 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% (one parameter 'cwd' fully described). Description adds no extra meaning beyond the schema, which is acceptable for a simple parameter.
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 lists 'locally saved automation scripts,' which is a specific verb-resource pair. It distinguishes from siblings like 'list_workflows' or 'list_pipelines' by specifying 'scripts' and 'local' scope.
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., when a script list is needed vs. other lists). 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?
Given no annotations, the description carries full burden but only mentions the source of workflows (global and workspace). It does not disclose if the operation is read-only, any required permissions, or side effects like cache updates.
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, efficient and front-loaded. However, it could be slightly clearer by breaking down the sources, but overall concise.
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?
The description is minimal for a list tool with no output schema and no annotations. It does not explain return format, filtering, or prerequisite workspace context, leaving significant gaps for an 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 adequate descriptions for 'cwd' and 'files'. The tool description adds no additional meaning beyond the schema, 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.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists workflows from two sources: global and from a workspace directory. It is specific about the resource and scope, distinguishing it from related tools like get_workflow_content.
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, such as other listing tools or when to filter results. It lacks any context about prerequisites or typical use cases.
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 does not disclose side effects, permissions required, or what happens upon cancellation (e.g., confirmation, impact on downstream steps).
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 short (one sentence) but lacks important details; it feels under-specified rather than efficiently concise.
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 the description does not indicate return values or behavior (e.g., confirmation message, error handling). For a 3-parameter tool, this is 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?
Parameter schema shows 100% coverage with descriptions for all three parameters. The description adds no extra meaning beyond the schema, so baseline 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 action ('Cancel') and the resource ('running pipeline'), which is specific and distinguishes from sibling tools like 'cancel_task' and 'cancel_schedule'.
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., cancel_schedule), no prerequisites mentioned, and no conditions for cancellation (e.g., can only cancel running pipelines).
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 bears full responsibility. It only states the action ('Delete') without disclosing side effects, reversibility, or permission requirements. For a destructive operation, more behavioral context is needed.
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 a single sentence with no wasted words, but it errs on the side of being too terse. It front-loads the purpose but omits helpful context that could be added without 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 tool's destructive nature, no output schema, and no annotations, the description is incomplete. It lacks information about error states, prerequisites, or what happens to dependencies, 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%, with both parameters (cwd and name) described in the input schema. The description adds no additional parameter meaning beyond what the schema already provides, so 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 'Delete a named agent resource group' uses a specific verb ('Delete') and resource ('agent resource group'), clearly distinguishing it from sibling tools like 'create_group' and 'list_groups'.
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 vs alternatives (e.g., delete_skill) or any preconditions. Siblings like create_group exist but no explicit usage context is given.
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 behavioral traits. It implies a read operation but does not explicitly state it is non-destructive or safe. Minimal transparency beyond the obvious list action.
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 with no wasted words, but slightly sparse. Could be improved by front-loading the key action and adding a brief note about usage.
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 list tool with two optional parameters and no output schema, the description adequately covers the return fields. Lacks mention of default behavior or formatting, but 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 coverage is 100%, so the schema fully describes both parameters (cwd and json). The description adds no additional parameter meaning, meeting the baseline 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 lists all scheduled tasks and specifies the fields returned (cron expressions, next run times, daemon status). It distinguishes from siblings like list_tasks by focusing on scheduled tasks, but does not explicitly differentiate.
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 siblings such as schedule_task or list_tasks. The description only states what it does without context 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?
No annotations are provided, so the description carries the full burden. It does not disclose effects on other data, permissions, or permanence of deletion. The path pattern is given but lacks 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 a single, direct sentence without fluff. It is appropriately brief for a simple tool, though could include a bit more context without becoming 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?
For a simple deletion tool, the description is minimally adequate. It lacks output format details and does not explain edge cases, but the presence of siblings and no output schema keep the bar moderate.
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 schema already describes all parameters. The description adds context for skill_name by specifying 'active workspace CLI skill' and the storage path, but does not enhance other 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 deletes an active workspace CLI skill by name, specifying the resource and location. It distinguishes from sibling tools like create_skill and list_skills by focusing on deletion.
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 disable or uninstall. Prerequisites like the skill being active or the workspace are 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 disclose behavioral traits. It does not state that this is a read-only operation, does not describe the return format, and does not mention any side effects, permissions, or limitations. The phrase 'active files tracked' is ambiguous regarding whether it returns file paths or metadata.
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 effectively communicates the core purpose without unnecessary words. It is front-loaded and easy to parse.
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 should provide more context about the return value, scope of 'active files', and how it differs from other tools. It is too brief to be fully actionable for an AI 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?
The schema covers 100% of the single parameter ('cwd') with its own description. The tool description adds no additional meaning beyond what the schema provides, so a neutral 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 'Return' and the resource 'active files tracked in the current project context'. This distinguishes it from sibling tools like track_files (adds files) and untrack_files (removes files).
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 gives no explicit guidance on when to use this tool versus alternatives. It implies that it lists current tracked files but does not mention when to avoid it or what makes it different from similar tools like 'get_board_state' or 'list_scripts'.
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 full behavioral disclosure. It states the tool lists groups with config, implying a read operation, but does not disclose authentication needs, rate limits, or any side effects. It lacks transparency beyond the basic function.
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 with no wasted words. It is concise but could be slightly more structured with hints about output format or usage context. However, it remains efficient 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?
The tool has no output schema, so the description should clarify what 'config' entails. It is minimally complete for a simple list operation, but lacks details about return format or examples. Given the number of sibling tools, it could be more helpful with context about when to use this versus search or filter 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%, so the baseline is 3. The description does not add meaning beyond the schema; it mentions 'config' but that is not a parameter. Parameters cwd and json are already described in the schema without additional context from the description.
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 lists all registered agent groups with their config, using a specific verb ('list') and resource ('registered agent groups'). This effectively distinguishes it from sibling tools like create_group, delete_group, and delegate_to_group.
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. Sibling tools include create_group, delete_group, and delegate_to_group, but the description does not mention contexts where listing is preferred or any exclusions (e.g., filtering, permissions).
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 bears the full burden. It describes a list operation but does not explicitly state that it is read-only, non-destructive, or what permissions are needed. The condition 'when the CLI exposes them' hints at potential unavailability, but not enough 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?
Two sentences that are efficient and front-loaded. The first states purpose, the second adds a practical usage hint. No redundant information, though it could be slightly more concise.
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 no output schema, the description should indicate what the tool returns (e.g., list of session IDs). It does not. The tool is simple with one parameter, but missing output information reduces completeness for an 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 description coverage is 100%: the one parameter 'cwd' is already described in the schema. The tool description adds nothing beyond that, so the baseline score of 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 'List available Antigravity CLI conversations for a project directory', identifying verb and resource. It also includes a condition 'when the CLI exposes them', which adds specificity. However, it does not define what a 'session' is, leaving some 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 provides a usage hint by connecting to delegate_task: 'Use session_id with delegate_task to resume.' This implies when to use the tool (to get session_id for resumption). However, it does not explicitly state when not to use it or compare with alternative listing tools like list_workflows or list_pipelines.
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 disclose behavioral traits. It states 'track active files' and 'persist file context' but does not explain whether tracking is additive or replaces previous state, any permissions needed, or side effects. This is insufficient for a tool with no annotation support.
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 sentences with no filler. The description is front-loaded with the action and purpose, then provides a use case. It is appropriately sized for a straightforward tool.
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 no output schema and no annotations, the description should cover more behavioral details. It captures the core purpose and use case, but lacks information on return value, idempotency, or error states. It is minimally complete for a 2-parameter 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?
The input schema covers both parameters (cwd and files) with descriptions, achieving 100% schema coverage. The description adds a usage context but does not elaborate on parameter meanings 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.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Track active files in local portal project state' and adds context about persisting file across pipeline steps. It distinguishes from siblings like 'untrack_files' and 'get_tracked_files' through the action verb and purpose, though 'track' could be more specific (e.g., add or set).
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 'useful to persist file context between pipeline steps,' which implies when to use. However, it does not provide explicit when-not-to-use or mention alternatives like 'untrack_files.' This is a minimal guidance.
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 bears full burden. It only says 'Get the current state', implying a read operation without disclosing any behavioral traits: side effects, authorization needs, or handling of invalid cwd. 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?
Single sentence, no wasted words. Front-loaded with key info. Perfect conciseness.
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 simple read tool with one parameter and no output schema, the description is minimally adequate. However, it lacks detail on what exactly the 'state' contains (e.g., task list, delegation hierarchy), which could be important for agent decisions.
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% (one parameter 'cwd' with description). The tool description adds no extra parameter meaning beyond the 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?
The description clearly states the verb 'Get' and the resource 'current state of the Agent Board', specifying it includes tasks and delegation tree. This distinguishes it from sibling tools like get_pipeline_status (pipeline-focused) or list_tasks (task list without delegation context).
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 vs. alternatives. No mention of context prerequisites, exclusions, or comparisons with similar tools such as list_tasks or get_pipeline_status.
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 the description must disclose behavioral traits. It only states the return content type, but fails to mention whether it's read-only, auth requirements, error handling, or side effects. For a 'get' tool, safety is implied but not confirmed.
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 unnecessary words. It efficiently conveys the core purpose, though slightly more detail could be added without harming conciseness.
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 exists, so the description should detail return value structure. It mentions 'markdown content and transition metadata' but omits format details, pagination, or error cases. Given the tool's simplicity and 3 required params, more context is expected.
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 descriptions for all three parameters. The tool description adds no further meaning beyond what the schema already provides, so 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 it returns 'markdown content and transition metadata for one workflow step node,' specifying a concrete verb and resource. It distinguishes from siblings like list_workflows and get_skill_content, which operate on different entities.
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?
No explicit when-to-use or when-not-to-use guidance is provided. Usage is implied by the purpose (retrieve step content), but no alternatives or exclusions are mentioned, leaving the agent to infer 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?
With no annotations, the description solely carries the burden for behavioral disclosure; it reveals only the basic action, omitting side effects, permissions, or state changes.
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?
A single efficient sentence that is front-loaded with the core action, containing no redundant words.
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 mutates pipeline state, the description lacks details on return values, error conditions, or consequences, making it incomplete for full contextual 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% and the description adds no additional parameter context 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 the verb 'return' and the resource 'task to a previous pipeline step', explicitly distinguishing it from sibling tools like cancel_pipeline or signal_step_complete.
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 when data is missing/insufficient but provides no explicit when-not-to-use or alternatives among siblings.
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 does not disclose behavioral traits such as error handling, read-only nature, or rate limits. The burden is on description but it offers no additional 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?
Single sentence with no filler or redundant information; perfectly concise.
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 status-check tool, the description is mostly adequate, though it could mention the output format or potential errors. No output schema exists but the tool is straightforward.
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 parameters are well-documented in schema. The description adds no extra 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 uses a specific verb 'Get' and resource 'status of a pipeline run,' clearly distinguishing it from sibling tools like cancel_pipeline or run_pipeline.
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; lacks context about prerequisites or conditions.
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 available, so the description must fully disclose behavior. It states the tool 'creates' a group with a configuration, but does not mention error handling for duplicate names, required permissions, side effects, or response format. This lack of detail leaves significant behavioral gaps for the agent.
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 with no wasted words. The first sentence states the primary action, and the second provides valuable context about reusability, front-loading essential 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?
The description explains the high-level purpose but lacks completeness for a tool with 16 parameters and no output schema. It does not mention how the created group fits into the workflow (e.g., for delegation), nor what the tool returns. While the schema covers parameter details, the overall context of use could be more 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?
With 100% schema coverage, the baseline is 3. The description adds no additional parameter details beyond what the schema already provides, which is sufficient but not enhanced.
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 'Create' and the resource 'named agent group' with additional context 'shared runtime config' and 'reusable presets for fractal orchestration'. It effectively distinguishes from sibling tools like list_groups, delete_group, and delegate_to_group.
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 by stating groups are reusable presets, but it does not explicitly specify when to use this tool versus alternatives (e.g., creating vs. listing or delegating). No when-not-to or prerequisite information is provided, leaving the agent with implied but not explicit guidance.
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?
Given no annotations, the description carries the burden of behavioral disclosure. It explains that reading is non-destructive by default and that 'clear=true' deletes messages after reading. It does not cover error states, rate limits, or idempotency, which are gaps.
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 about 5 sentences, front-loaded with the main purpose. Every sentence adds value, including the channel conventions and the clear option. No fluff or redundancy.
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?
Without an output schema, the description fails to specify the return format or structure of messages (e.g., plain text, JSON). It also does not mention error conditions or edge cases. This is a significant gap for agent decision-making.
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 by explaining the channel naming conventions and the effect of 'clear', which are not fully captured in the schema's parameter descriptions. This elevates it.
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 states the verb 'Read' and resource 'messages from a channel', and adds 'Returns all messages in chronological order,' making the purpose clear. It distinguishes from sibling 'send_message' without explicit comparison. Could be more specific about the nature of messages.
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 channel naming conventions (run_id, step_name) and explains the 'clear' parameter for consumption, which guides usage. However, it does not mention when to use this tool vs alternatives or any preconditions, leaving some ambiguity.
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 the full burden. It discloses that the tool returns the last 20 newest results, but it does not mention whether the operation is read-only, any authentication needs, rate limits, or side effects. This is insufficient for safe and reliable 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 two sentences with no wasted words. The purpose is front-loaded, and the key behavioral detail (last 20, newest first) is included efficiently.
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 3 parameters, no output schema, and no annotations, the description is minimal. It covers the basic purpose and a key constraint (limit 20), but lacks information about pagination, error handling, or the relationship to other scheduling tools. It is adequate but not comprehensive.
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 schema already documents all parameters. The description does not add any additional meaning beyond what the schema provides (e.g., clarifying the format of schedule_id or the effect of cwd). 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 verb 'Get' and the resource 'results from scheduled task executions', with specific detail about returning the last 20 results newest first. This distinguishes it from sibling tools like schedule_task or cancel_schedule, which deal with scheduling rather than retrieving results.
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 viewing recent scheduled results via the mention of 'last 20 results, newest first', but it does not provide explicit when-to-use or when-not-to-use guidance, nor does it mention alternatives like get_task_result. This leaves the agent to infer appropriate usage 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 must cover behavioral traits. It mentions that operations are done 'without loading full markdown' and returns indexes, but does not disclose side effects, permissions, or rate limits. Basic transparency is present but not comprehensive.
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, front-loaded sentence with no waste. However, it omits crucial usage guidelines and behavioral details, which slightly reduces conciseness value.
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 8 parameters, no required parameters, and no output schema, the description is too brief. It does not explain return format, behavior when called with defaults, or how to interpret the results. Important context 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 baseline is 3. The description adds minimal additional meaning beyond the schema; it does not explain how parameters like cwd or mode affect the behavior in more 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 it returns a compact dynamic context plan, classifies zones, recommends tool profile, and returns matching skill/workflow indexes. This is specific and distinguishable from siblings like list_workflows or search_by_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?
The description does not explicitly state when to use this tool versus alternatives. While it implies usage for obtaining a context plan, no guidance on when not to use or comparison with siblings like search_by_tags or list_workflows 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 provided, the description carries full burden. It conveys the basic action but does not disclose potential side effects (e.g., files are only untracked, not deleted), required permissions, or error conditions. 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?
Single sentence, zero waste. Every word earns its place. Efficient and 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?
For a simple tool with 2 parameters and no output schema, the description is adequate. It specifies the action and context. Minor missing detail: could clarify that 'untrack' does not delete files. Still complete enough for typical use.
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 parameters are well-documented. The description adds no extra meaning beyond schema, such as format constraints or usage nuances. Baseline 3 applies as schema does the heavy lifting.
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 'Remove files from the active tracking context' uses a specific verb 'remove' and resource 'files' within a clear context. It effectively distinguishes from the sibling 'track_files' which adds files.
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 removing tracked files but offers no explicit guidance on when to use this tool vs alternatives like 'track_files' or 'get_tracked_files'. No when-not-to-use or alternative naming.
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 reveals that the tool lists both running and recently completed tasks and that they are stored in 'agent pool memory'. However, it does not explain what qualifies as 'recently completed' or whether repeated calls yield consistent results. Without annotations, more detail about idempotency or caching would 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 a single clear sentence with 12 words, no redundancy. It efficiently conveys the core functionality.
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 no output schema, the description should clarify what data is returned for each task. It lacks details like fields, pagination, or limits. The phrase 'recently completed' is vague. Overall adequate but could be more complete.
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?
There are no parameters in the schema, so parameter information is not needed. The description does not add parameter-specific meaning, but with zero parameters the baseline is 4.
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 'list', the resource 'background tasks', and the scope 'currently running or recently completed in the agent pool memory'. It distinguishes itself from sibling tools like 'cancel_task' and 'list_pipelines' by specifying background tasks and memory scope.
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 'get_pipeline_status' or 'list_sessions'. No mention of when not to use or side effects.
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?
Discloses return behavior (full content vs lightweight list) but no annotations exist. Missing details on destructive nature, auth needs, or 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: first states purpose, second describes return behavior. 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?
Core functionality and return format are clear, but no output schema, no mention of pagination, error handling, or format of lightweight list.
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 all parameters with descriptions; description adds only that tags use AND semantics, which is already in schema. Baseline 3 due to high coverage.
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 it finds workflow steps matching all tags, with specific return behavior for single vs multiple matches. Distinct from sibling tools which focus on pipelines, sessions, tasks, etc.
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 AND semantics for tags but does not explicitly state when to use vs alternatives (e.g., search by other criteria) or provide when-not guidance.
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 mentions return content; fails to disclose error behavior, permission requirements, or side effects of loading. As a read tool, safety is implied but not explicit.
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 stating purpose and usage context. No wasted words, front-loaded with key action and resource.
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, description mentions return includes metadata and markdown content. Usage guidance ties to resolve_context. Could elaborate on error handling but sufficient for the tool's simplicity.
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 100% of parameters with descriptions. The tool description adds context about using after resolve_context, but this is also hinted in the name parameter description. Adds marginal value 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?
Clearly states verb 'Return' and resource 'one global or active workspace skill with metadata and markdown content'. Distinguishes from list_skills by specifying atomic loading of a single item.
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 advises to use after resolve_context returns a skill item needing atomic loading. Provides clear context for invocation but does not explicitly list 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.
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 correctly describes a read-only listing operation without side effects, but lacks details about authorization or output format beyond the schema parameters.
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 with no waste, front-loading the core purpose and key distinction between global and project-specific skills.
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 list tool, the description adequately covers what is listed and where from, though it could mention that output may be Markdown or JSON (handled via json parameter). It is sufficient 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%, so baseline is 3. The description does not add meaning beyond the schema; it only mentions the cwd parameter implicitly via the workspace reference.
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 'list' and the resource 'skills', specifying two sources: global CLI skills and skills from the team-memory workspace directory. This differentiates it from sibling list tools like list_workflows.
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 listing skills but does not explicitly state when to use it over alternatives like get_skill_content or create_skill, nor does it provide exclusions or prerequisites.
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 carries full burden. It states the action and destination but lacks details on overwrite behavior, permissions required, or side effects. Adequate 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?
Two sentences, concise and front-loaded. No wasted words, clearly communicates purpose and context.
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 simplicity (4 params, no output schema, no annotations), the description is adequately complete. It could mention return value or success confirmation, but overall 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 coverage is 100% with descriptions for all parameters. Description adds no new details beyond the schema, 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?
Description clearly states verb (save), resource (local automation script), and destination (team-memory scripts/). It also notes utility for zero-token execution nodes, distinguishing it from sibling tools like list_scripts or create_skill.
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 usefulness for zero-token execution nodes but does not explicitly state when to use or when not to use, nor does it compare with sibling tools like create_skill or list_scripts.
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 signals step completion, but does not describe side effects, required permissions, or what happens after signaling. For a simple signaling tool, this is 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?
A single 14-word sentence that efficiently conveys purpose and caller context. 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?
No output schema is present, and the description does not mention return values or error behavior. With 5 parameters (1 required) and no annotations, more details on expected outcomes would improve completeness, but the core function is clear.
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 documented in the schema. The description does not add additional meaning beyond the 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?
The description clearly states the verb 'signal', the resource 'pipeline step', and importantly specifies the caller context: 'called BY agents running inside pipeline steps'. This distinguishes it from sibling tools like 'get_pipeline_status' or 'cancel_pipeline'.
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 explicitly states that this tool is called by agents inside pipeline steps, providing clear usage context. Although it doesn't list alternatives or when not to use it, the context is specific enough to guide correct invocation.
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 removal from schedule and daemon auto-exit when no schedules remain. With no annotations, this provides useful behavioral context. Could be improved by noting what happens on invalid schedule_id 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?
Three concise sentences covering purpose, removal, and daemon behavior. No unnecessary words, front-loaded with the core 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?
Covers the main action and a key behavioral consequence (daemon auto-exit). Without output schema, some info on return values or error handling is missing, but sufficient for correct 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 coverage is 100%, and the description does not add extra meaning beyond the schema definitions. Baseline 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?
Clearly states 'Cancel a scheduled task by ID' which is a specific verb+resource. Distinguishes from siblings like cancel_task and cancel_pipeline by mentioning 'scheduled task' and the daemon auto-exit effect.
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?
No explicit when-to-use or when-not-to-use guidance compared to siblings. The domain implies use for scheduled tasks, but does not guide the agent on selecting this over cancel_task or cancel_pipeline.
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 discloses the destructive action ('kill its process') but does not mention side effects, authorization needs, or error conditions. Acceptable but not rich.
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, minimal waste, front-loaded with action and context. Every sentence serves a purpose.
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 one parameter, no output schema, and simple behavior, the description is adequate. It covers purpose and usage but doesn't describe return behavior or failure modes.
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 meaningful semantics beyond the schema's 'Task ID to cancel.' It could detail format or constraints.
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 (cancel a running task) and the resource (task), using specific verb 'kill its process'. It distinguishes from sibling tool cancel_pipeline which operates on a different resource.
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 explicitly provides when-to-use guidance: 'Use when a task is stuck or no longer needed.' It lacks explicit when-not-to-use or alternative tools, but siblings help further.
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 key behavior: returns array of task_ids immediately (non-blocking), and spawns agents with group config. However, it does not mention error conditions, prerequisites, or side effects like permission needs.
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: first states core purpose, second gives a usage hint, third explains return behavior. No unnecessary words, well-structured, and efficient.
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 tool with 20 parameters and no output schema, the description covers the overarching behavior (delegation, parallelism, non-blocking). It misses details on parameter interactions but schema provides per-parameter descriptions, making the overall definition reasonably 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 baseline is 3. The description adds value by explaining 'count' for parallel execution and the return behavior, but does not elaborate on many other parameters beyond what 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 uses specific verb 'delegate' and resource 'named agent group', and mentions 'spawns agents with shared config'. This clearly distinguishes from siblings like delegate_task (which likely delegates to a single agent) and delegate_task_readonly.
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 context for when to use 'count' for parallel spawning and notes the non-blocking nature with a pointer to get_task_result. However, it does not explicitly state when not to use this tool or compare 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?
Without annotations, description covers daemon persistence and result storage. But it lacks details on permissions, resource implications, or side effects of scheduling autonomous tasks. Adequate but not comprehensive.
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?
Five sentences efficiently convey core purpose, behavior, and examples. No redundancy. Slight room for improvement by front-loading the most critical information, but overall well-structured.
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?
With 10 parameters and no output schema, the description covers main functionality but omits return value (e.g., schedule ID) and does not explain 'delayed one-shot' fully. Some advanced parameters like catchup, serviceTier, reasoningEffort are not addressed.
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 all parameters (100% coverage), so baseline is 3. Description adds value with cron format guidance, provider defaults, and some mapping details (e.g., model to service_tier).
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 verb 'schedule', resource 'CLI agent', and schedule type 'cron or delayed one-shot'. It also specifies the default provider, distinguishing it from siblings like cancel_schedule and get_scheduled_results.
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 explains when to use the tool (to schedule tasks) and provides cron format examples. However, it does not explicitly state when not to use it or suggest alternatives, though the context of siblings is informative.
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 behaviors: non-blocking, sandboxed to cwd, ability to add directories via include_dirs, shell access outside workspace, startup delay, and recommended timeout values. Lacks details on error handling or rate limits but covers major 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?
The description is well-structured: first sentence states purpose, followed by sandbox constraints, use cases, async behavior, and important notes. It is relatively concise given the complexity, though some details could be more streamlined. No wasted sentences.
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 (23 parameters, no output schema), the description provides a good overview of the workflow, including async polling via get_task_result. It covers startup delay, workspace scope, and timeout advice. Could be more explicit about error scenarios 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 baseline is 3. The description does not add significant parameter-specific explanations beyond what the schema already provides. It mentions workspace and timeout in a general sense but does not elaborate on individual 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's purpose: delegating a coding task to a CLI agent in headless mode. It specifies the verb 'delegate', the resource 'coding task', and the asynchronous nature (non-blocking, returns task_id). It distinguishes itself from siblings like delegate_task_readonly and get_task_result.
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 explicit use cases: 'Use this for parallel work: code review, testing, refactoring, analysis, or any dev task.' It also advises on timeout settings and warns about startup delay. However, it does not explicitly contrast with delegate_task_readonly or other alternatives, leaving some ambiguity.
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 discloses that results persist until TTL cleanup and that multiple callers can retrieve the full report. It does not discuss error handling or auth requirements, but the disclosed persistence and multi-caller support are valuable 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?
Two sentences, front-loaded with the primary action, no redundant wording. 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?
Given no output schema, the description would benefit from describing the report format or response structure. It covers usage and result persistence adequately but omits details about what the 'full report' contains. Completeness is moderate.
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 does not add meaning beyond the schema's description of task_id. The baseline of 3 is appropriate as the schema already documents the parameter sufficiently.
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 'check' and the resource 'status and result of a background task', and distinguishes it by specifying the initiating tools (delegate_task, delegate_task_readonly, consult_peer). This differentiates it from sibling tools like cancel_task or get_pipeline_status.
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 that this tool is used after starting a background task with specific delegating tools. However, it does not explicitly state when not to use it or contrast with alternatives like cancel_task. The guidance is clear but lacks exclusion criteria.
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 exist, so the description carries full burden. It discloses default actions (cancel running tasks, keep results for completed) and the effect of 'remove_from_memory'. It could mention more about process cleanup side effects, but it's transparent enough 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, front-loaded with the action, no redundancy. Every sentence contributes essential 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 the complexity (4 parameters, no output schema) and no annotations, the description covers core behavior and defaults. It omits details like return values or what 'clean up' entails in terms of memory, but it is nearly complete for the tool's scope.
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 schema already documents each parameter. The description adds value by explaining defaults and overall flow, but does not provide additional constraints, examples, or relationships 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 uses specific verbs ('Close', 'clean up') and specifies the resource ('task lifecycle', 'tracked child processes'), clearly distinguishing from sibling tools like 'cancel_task' which might only cancel without lifecycle closure.
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 default behaviors for running vs completed tasks and the 'remove_from_memory' effect, providing clear context on when to use. It lacks explicit 'when not to use' or alternative tool names, but the context 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?
No annotations provided, so description carries full burden. It discloses the return type (examples per topic) and default behavior (full guide if topic omitted), but lacks details on side effects, permissions, or performance implications. For a read-only guide tool, 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, each with distinct value: purpose, when-to-use, return type, parameter options. No redundancy, 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?
For a simple informational tool with one optional parameter and no output schema, the description covers purpose, usage, and parameter semantics effectively. Could mention output format explicitly, but not critical.
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 describes topic parameter with list of topics. Description adds the default behavior of omitting topic to get full guide, which provides extra guidance 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 a comprehensive usage guide with examples and best practices, distinguishing it from sibling action 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 instructs to call this FIRST when planning parallel work, pipelines, or scheduling. No when-not-to-use or alternatives mentioned, but strong usage context.
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 transparently discloses that the tool is 'reserved for future' – indicating it likely performs no action currently. It also clarifies that workspace skills are managed elsewhere, avoiding unintended use.
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 sentence long, efficient, and immediately conveys the purpose and context. No redundant words.
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 is a placeholder, the description adequately covers its reserved nature, current non-functionality, and alternative methods. No output schema 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% (all 3 parameters documented). The description adds minimal value beyond the schema, only hinting that skill_name refers to external skills. Baseline 3 is appropriate given high coverage.
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 is 'Reserved for future external skill installation' and distinguishes it from managing workspace skills via team-memory or Agent Portal UI. This provides a specific verb+resource and differentiates from sibling 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?
The description implies not to use this tool for workspace skills by pointing to alternatives, but lacks explicit when-to-use guidance for the future external installation scenario. However, it clearly advises against current misuse.
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 discloses idempotency, best-effort semantics, and response for unknown/already-released admissions. Could provide more on permissions or side effects but is 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?
Three sentences pack essential information: purpose, idempotency behavior, and usage context. No wasted words.
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 no output schema, the description mentions return shape ('released:false with ok:true') and explains the tool's raison d'être. Single parameter is well described.
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 minimal value beyond the schema's parameter description. 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 'Release a capacity slot in the cross-process slot ledger for a given admission_id', specifying the exact verb and resource. It distinguishes from siblings as no other tool handles slot release.
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?
Describes idempotent and best-effort nature, and when the board calls it ('when a workflow step closes'). However, lacks explicit when-not-to-use or alternative tool references.
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 provided, the description fully carries the burden of behavioral disclosure. It reveals that messages are persisted to disk, survive restarts, and use JSONL format for concurrent-write safety, adding critical context beyond the 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 concise (three short paragraphs) and well-structured, with each sentence serving a purpose: stating the action, usage context, channel conventions, and persistence details. No 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?
The description covers channel usage, persistence, and concurrency safety. However, since there is no output schema, it does not mention what the tool returns (e.g., success confirmation), which is a minor gap for completeness.
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 by explaining channel conventions (broadcast vs targeted) and noting payload can be any JSON-serializable value, enhancing parameter understanding 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 tool sends a message to a channel for inter-agent communication, specifying the verb 'send' and resource 'channel'. It also distinguishes from siblings like get_messages (receiving) and signal_step_complete (different purpose) by focusing on sending structured data between pipeline steps or agents.
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 explicit guidance on when to use this tool ('between pipeline steps or between any agents') and details channel conventions for broadcast vs targeted messaging. While it doesn't explicitly mention when not to use it or compare to alternatives, the context is clear enough for an agent to decide.
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?
No annotations provided, so the description carries full burden. Discloses non-blocking nature, provider startup delay, workspace restrictions (cwd + include_dirs), and that shell commands can access other paths. Also explains similarity to delegate_task.
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 purpose first, then behavior, then important notes. Slightly long but all information is relevant and no redundancy.
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 19 parameters and no output schema, the description explains return behavior, workspace, timing, and provider options. It is sufficiently complete for correct tool 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% with all parameters described. The description adds value by explaining workspace behavior and recommending use of include_dirs, complementing the schema details.
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 'Delegate a read-only analysis task to a CLI agent' and distinguishes itself from the sibling 'delegate_task' by noting it is semantically identical but signals analysis intent.
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 use cases (code review, architecture analysis, etc.), mentions how to retrieve results with get_task_result, and gives timeout recommendations. However, it does not explicitly state when to prefer delegate_task over this tool.
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?
No annotations exist, so description carries full burden. It discloses non-blocking behavior, returns task_id, supports iterative rounds, no timeout, and progress via get_task_result. The verdict types (AGREE, SUGGEST_CHANGES, DISAGREE) are specified.
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?
Every sentence adds unique information. Front-loaded with purpose, then usage, then behavioral details. No wasted words; efficient and structured.
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?
Despite no output schema, description covers return values (task_id and verdict) and explains how to retrieve results (get_task_result). Also mentions progress visibility, making it complete for this 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 context beyond definitions: explains 'context' as project context, 'proposal' as technical proposal, and introduces 'previous_rounds' for iterative use. Adds value without redundancy.
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 defines the tool as 'Antigravity-backed peer consultation for architectural/technical consensus' and specifies its use in the PLANNING phase for validating proposals. It distinguishes itself from siblings by contrasting with 'delegate_task_readonly'.
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 when to use (PLANNING phase) and provides a clear alternative: 'prefer delegate_task_readonly with resource_group: "review"' for Codex orchestration. This gives direct guidance on tool selection.
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:

[![agent-pool-mcp MCP server](https://glama.ai/mcp/servers/rnd-pro/agent-pool-mcp/badges/card.svg)](https://glama.ai/mcp/servers/rnd-pro/agent-pool-mcp)

Score Badge

Copy to your README.md:

[![agent-pool-mcp MCP server](https://glama.ai/mcp/servers/rnd-pro/agent-pool-mcp/badges/score.svg)](https://glama.ai/mcp/servers/rnd-pro/agent-pool-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/rnd-pro/agent-pool-mcp'

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