Server Quality Checklist

Tool Scores

• list_recent_runsA
  3.8/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations already declare readOnlyHint=true, so description's 'lists' is consistent. Description adds filter options and return fields but does not mention pagination behavior, default ordering, or rate limits. No contradiction.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two concise sentences front-loading the core purpose and available filters. No fluff, every word adds value.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  With 9 parameters and no output schema, the description covers the main filters and returned fields. However, it omits pagination details (limit/offset) and default sort order, which are useful for an agent to know 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 56%; description summarizes filter categories (status, agent, etc.) but does not explain individual parameters like limit/offset beyond what is in the schema. Adds marginal value.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Directly states the function: listing simulation runs with optional filters and specifies the returned fields. Clearly distinguishes from siblings like get_run_details (single run) and list_agents.

  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?

  Lists available filters but does not explicitly guide when to use this tool versus siblings (e.g., get_run_details for a single run, preview_run_cost for cost estimation). No when-not or alternative tool mentions.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• get_run_detailsA
  3.9/5.0
  Behavior3/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations declare readOnlyHint=true, consistent with a fetch operation. Description adds that it includes status and evaluation results when available, but doesn't elaborate on other behavioral traits like idempotency or lack of 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, front-loaded with the primary purpose, and 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?

  With no output schema, the description could benefit from more detail about the structure of the returned details. It only mentions status and evaluation results, leaving other 'full details' unspecified.

  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 the single parameter. The description adds no additional meaning beyond what is 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?

  Clearly states it fetches full details of a single simulation run, distinguishing it from sibling tools like list_recent_runs which lists runs, and evaluate_agent which evaluates 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?

  Explicitly advises 'Use after a run to inspect scores and outcome,' giving clear context for when to use. Lacks explicit alternatives or when-not-to-use guidance.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• evaluate_agentA
  4/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Discloses blocking nature (30s–5min), cost preview, simulation run, wait, and return of scores. Also mentions optional timeout override. Annotations are minimal (readOnlyHint: false, destructiveHint: false), so description adds useful behavioral context, though it omits whether the run is saved 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 sentences, front-loaded with core function, second sentence adds parameter guidance. No redundant words; every sentence adds 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?

  No output schema, so description should describe return values more thoroughly (e.g., what scores are returned). Also misses mentioning the num_runs parameter entirely. Leaves gaps for a blocking evaluation 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%, so baseline 3. Description adds workflow context (preview cost, run, wait, return scores) that enriches parameter understanding beyond schema descriptions. However, it does not detail num_runs parameter.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description clearly states the verb 'runs and evaluates', the resource 'agent against a scenario', and distinguishes from siblings like 'delete_scenario' or 'preview_run_cost' by specifying it does full end-to-end evaluation blocking until completion.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Implies usage via 'Give it an agent uuid and a scenario uuid', but no explicit when-to-use or when-not-to-use compared to alternatives like 'preview_run_cost' for cost-only queries. No exclusions or prerequisites stated.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• generate_scenarioA
  4.2/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations indicate it's not read-only or destructive. The description adds significant behavioral context: blocking behavior (30s-2min), return values (uuid or batch uuids), and structured error on failure. No rate limits or auth details are disclosed, but overall adds value beyond annotations.

  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 compact (two sentences), front-loaded with the core purpose, and every sentence adds value. No redundant or vague statements.

  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, the description adequately explains return values. It covers essential parameters (type, tags, num_scenarios, tag_pool) but omits explicit mention of some batch-specific parameters. However, schema fills the gaps, making it sufficiently complete for a user.

  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 78%, so schema provides most parameter details. The description adds context about batch mode and tag_pool requirement, but does not elaborate on parameters like total_tags, include_tags, or max_tags_per_npc beyond what the schema covers.

  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 generates a new test scenario, specifies the scenario types (info_exchange or interview), and mentions optional parameters. It distinguishes itself from sibling tools like delete_scenario and evaluate_agent by focusing on creation.

  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 guidance on batch mode (num_scenarios > 1 requires tag_pool) and typical blocking time, but does not explicitly state when not to use the tool or mention alternatives like list_compatible_tags for parameter selection.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• list_agentsA
  4.2/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations already declare readOnlyHint=true, and the description aligns by describing a read-only list operation. It adds context on return fields, which is useful. No further behavioral details are needed given the annotation coverage.

  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 cover purpose, filtering, and return fields. No redundant information, and the key points are front-loaded. Every part is necessary.

  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 low complexity (3 optional params, no output schema), the description covers the main functionality and return fields. Lacks explicit pagination explanation, but the schema parameters imply it. Overall sufficient for the tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The description explains the agent_type parameter and its enum values, but does not mention limit or offset parameters. With schema description coverage at 33%, the description partially compensates but could be more complete on pagination context.

  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 AI agents in the workspace, with an optional filter by connector type. It specifies the return fields (uuid, name, type, URL), making it distinct from sibling tools like register_agent or delete_scenario.

  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 when to use this tool (to list agents, optionally filtered), but does not explicitly provide when-not-to-use or alternatives. It lacks guidance on pagination or cost implications, but the context is clear enough for basic usage.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• register_agentA
  4.2/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  The description adds value beyond annotations by detailing that A2A agents are verified for reachability and DIRECTLINE/MCP agents are probed before creation. It also warns that credentials transit the conversation. Annotations already indicate a non-read, non-destructive operation.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise (3-4 sentences), front-loaded with the main purpose, and efficiently covers probing behavior, return information, and a security note. No unnecessary words.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's complexity (17 parameters, nested objects, no output schema), the description covers essential aspects: purpose, connector-specific behavior, security, and return value. It could be improved by mentioning error conditions or idempotency, but it is sufficiently complete for effective 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?

  With only 35% schema description coverage, the description adds some context by explaining connector types and sensitivity of credentials, but it does not individually describe the majority of parameters. The description partially compensates for low schema 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 explicitly states 'Registers an AI agent in VerifyAX given its name, connector type...' providing a specific verb and resource, and distinguishes the tool from sibling tools which focus on scenarios, runs, and evaluation.

  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 clearly indicates when to use the tool (registering agents) and provides context on probing behavior for different connector types. However, it does not explicitly state when not to use it or mention alternatives.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• list_compatible_tagsA
  4.3/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations already declare readOnlyHint=true. The description adds value by detailing the return structure (name, category, description) and special flag for QnA tags. No contradictions.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences, front-loaded with action. Every sentence adds meaningful information with no waste.

  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 full schema coverage, annotations, and description covering output structure and special behavior, the description is fully adequate for this simple tool.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% with the only parameter scenario_type having a clear description. The description does not add any additional semantics beyond the schema, 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 the tool lists skill tags for a given scenario type (info_exchange or interview). It uses a specific verb ('lists') and resource ('skill tags'), and the purpose is unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicitly says 'Use this before generating a scenario to pick valid tags,' providing clear when-to-use guidance. It does not list when not to use or alternatives, but the sibling generate_scenario is an obvious counterpart.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• delete_scenarioA
  4.4/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations already indicate destructiveHint=true and idempotentHint=true. The description adds value by specifying irreversibility and the failure condition, and notes that a confirmation is returned. No contradictions.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three concise sentences, each adding value: action, constraints, and return behavior. No wasted words, front-loaded with the main 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?

  For a simple delete tool with one parameter, the description covers irreversibility, precondition, and return. Without an output schema, mentioning confirmation is helpful. Could elaborate on what the confirmation contains, but it's adequate.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  With 100% schema coverage and the parameter description already included in the schema, the tool description adds minimal new information about the parameter. The schema already describes 'The uuid of the scenario to permanently delete.' Baseline 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action 'permanently deletes a scenario' with the specific identifier 'by its uuid', which distinguishes it from sibling tools like generate_scenario or list_compatible_tags. The verb and resource are explicit.

  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 important usage context: the deletion is permanent and 'fails if simulation runs still reference the scenario'. This tells the agent when not to use it (if referenced). It could be improved by stating when to use it, but the prerequisite is clear.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• preview_run_costA
  4.4/5.0
  Behavior5/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  Annotations declare readOnlyHint=true, and description reinforces it's only an estimate without executing. Discloses return fields (estimated credits, balance, pending committed spend). No contradiction.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences, front-loaded with main purpose, then specific details. Every sentence adds value; no filler.

  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 adequately states what is returned. For a preview tool with read-only semantics and well-documented params, it's sufficiently complete.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so description adds limited additional meaning. Reiterates timeout_minutes range (1–240) and its effect on estimate, but other parameters (num_runs, agent_uuid, scenario_uuid) are not elaborated 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 it estimates credit cost before running an agent against a scenario. Verb 'estimates' + resource 'credit cost' is specific. Distinguishes from sibling tools like evaluate_agent or get_run_details.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicitly says 'before triggering it', indicating when to use. Mentions optional timeout_minutes affects estimate. No explicit when-not or alternatives, but context provides sibling names.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.