Server Quality Checklist

Tool Scores

• search_trialsA
  3.6/5.0
  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 It discloses that withdrawn/terminated trials are excluded by default and that results are ordered with recruiting first. However, it does not mention rate limits, authentication, or whether the search is paginated, which are relevant for a network search tool.

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

  Conciseness5/5

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

  Three sentences, no fluff. Front-loaded with purpose, then key details. Every sentence contributes value.

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

  Completeness4/5

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

  Given no output schema, the description includes what fields are returned (status, phase, sponsor, site count, brief summary). It covers default filtering and ordering. It lacks mention of error handling or empty results, but is otherwise complete for a search tool.

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

  Parameters3/5

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

  Schema coverage is 100%, so baseline is 3. The description adds context for the 'status' parameter (default exclusion behavior) and mentions result ordering, but does not significantly enhance the meaning of other parameters beyond what the schema already provides.

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

  Purpose4/5

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

  The description clearly identifies the verb 'Search' and resource 'ClinicalTrials.gov for trials matching a condition', and lists fields returned. It implicitly distinguishes from siblings like 'find_recruiting_near' by mentioning ordering with RECRUITING first, but does not explicitly contrast with other siblings.

  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 states default behavior (exclusion of WITHDRAWN/TERMINATED) and how to override with status, but does not explicitly state when to use this tool versus alternatives like 'compare_trials' or 'find_recruiting_near', nor does it mention prerequisites or context.

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

• compare_trialsA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries full burden. It describes the output (structured tables) but does not disclose behavioral traits like idempotency, rate limits, or auth requirements. The description is adequate but lacks depth for a complete behavioral picture.

  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 purpose, no fluff. Every sentence earns its place.

  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 describes output as structured tables with listed categories. However, it misses behavioral context like whether it is read-only or if results are cached. Almost complete for a comparison 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 the schema already documents both parameters. The description adds minimal value beyond schema, only reiterating the purpose of 'compare_on'. 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 compares 2 to 5 clinical trials side by side, producing structured tables for specified categories. It distinguishes from sibling tools like 'get_trial_details' (single trial) and 'search_trials' (search) by focusing on comparison.

  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 using the 'compare_on' parameter to focus on a category, but does not explicitly state when to use this tool over siblings (e.g., when comparing multiple trials vs. getting details of one). This leaves some ambiguity.

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

• get_trial_detailsA
  4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It transparently lists the types of data returned (overview, eligibility, sites, results) and the hyperlink feature. It does not mention error handling, rate limits, or whether it requires authentication, but for a read-only retrieval tool, the level of detail is good.

  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: the first states the core purpose, the second lists what's included. No redundant phrases, every word adds value. 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.

  Completeness4/5

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

  Given no output schema and low complexity, the description covers the main return data points adequately. It could mention data source or behavior on missing NCT ID, but for a single-parameter retrieval tool, it is sufficiently complete.

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

  Parameters3/5

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

  The schema already fully describes the single parameter (nct_id with example and case-insensitivity). The description does not add additional semantics beyond restating that it's by NCT ID. Since schema coverage is 100%, the 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 tool retrieves a full structured summary of one clinical trial by NCT ID. It lists the specific components returned (overview, eligibility criteria, site locations, results), which distinguishes it from siblings like search_trials (multiple trials) or compare_trials (comparison). The mention of an NCT ID hyperlink adds value.

  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?

  Usage context is implied: use when you have an NCT ID and want a detailed summary. However, the description does not explicitly state when to use this over siblings (e.g., search_trials for broad search, get_trial_results for results only). No exclusions or alternatives are mentioned.

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

• find_recruiting_nearA
  4.1/5.0
  Behavior5/5

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

  No annotations provided, so the description carries full burden. It clearly discloses key behavioral traits: grouping by location rings, city/country-level limitation, and the critical distinction between trial-level and site-level recruitment status. This adds significant context beyond the input schema.

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

  Conciseness5/5

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

  Extremely concise: two clear sentences plus a necessary caution. Front-loaded with the main purpose, then key behavioral details. No wasted words.

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

  Completeness4/5

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

  Given no output schema and four parameters, the description covers the tool's behavior well, including limitations and a critical caveat. Could mention pagination or error handling, but for a straightforward search tool this is sufficient.

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

  Parameters3/5

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

  Schema description coverage is 100%, so baseline is 3. The description does not add significant per-parameter semantics beyond what the schema already provides (e.g., condition, location, phase, max_results). The note about location granularity is helpful but not new parameter-level detail.

  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?

  Clearly states the tool finds actively recruiting trials for a condition near a location, including grouping by location rings. However, it does not explicitly distinguish from sibling tools like search_trials or get_trial_results, which could be used for broader or different purposes.

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

  Usage Guidelines4/5

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

  Provides important usage guidance: location is city/country level, no GPS radius, and warns about overall trial status vs site status. Does not explicitly state when not to use or list alternatives, but the caveat is valuable for correct usage.

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

• get_trial_resultsA
  4.1/5.0
  Behavior4/5

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

  The description discloses the tool's behavior for four distinct cases and the default adverse event filtering, which adds value beyond the schema. However, it lacks details on error handling or other behavioral traits, though no annotations exist to carry that burden.

  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 two sentences that front-load the main purpose and efficiently cover key details like the four cases and default AE grade.

  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?

  For a tool with no output schema, the description adequately explains what the tool returns (components of results and cases), making it complete for an agent to understand the tool's function.

  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 description adds minimal extra meaning beyond the schema. It restates the default for ae_grade but does not significantly enhance understanding of parameter semantics.

  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 fetches posted results for a clinical trial, listing specific components like participant flow, baseline characteristics, and outcomes, distinguishing it from siblings like get_trial_details.

  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 indirectly implies usage by listing the four cases it handles, but it does not explicitly state when to use this tool versus alternatives like get_trial_details or compare_trials.

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