Server Quality Checklist

Tool Scores

• query_rcsb_apiA
  3.6/5.0
  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 mentions it returns a JSON string but does not disclose whether the operation is read-only, any authentication requirements, rate limits, or error handling behavior. For a query tool, these are important gaps.

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

  Conciseness4/5

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

  The description is well-organized with sections for Args, common endpoints, and Returns. It is reasonably concise given the need to cover a generic tool, though it could be tightened by removing some redundancy.

  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 generic tool, the description gives essential usage details and return type, but lacks guidance on error handling, authentication, rate limits, and potential side effects. Since there is no output schema provided, it should also clarify the response structure beyond just 'JSON string'.

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

  Parameters4/5

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

  Schema description coverage is 0%, but the description compensates well by explaining the endpoint format (with examples) and the params as an optional JSON string. It provides common endpoint patterns, giving the agent enough context to construct valid calls.

  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: 'Make a custom query to the RCSB Data API' and positions it as an advanced direct-access tool for any endpoint. This distinguishes it from the specific sibling tools (e.g., get_pdb_entry, get_polymer_entity) by its generic nature.

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

  Usage Guidelines3/5

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

  The description implies use for advanced/custom queries with 'advanced tool' and 'any endpoint', but does not explicitly state when to prefer this over the more specific siblings or when not to use it. It lists common endpoints but omits guidance on selecting this tool vs. alternatives.

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

• search_pdb_by_organismA
  3.7/5.0
  Behavior4/5

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

  The description transparently states what the tool returns: 'Instructions and example queries for searching by organism'. This makes clear that the tool does not perform a search itself but provides guidance. There is no mention of side effects or side effects are not applicable. Given the simple nature of a guidance tool, the description adequately discloses the outcome of invoking it.

  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 succinct and well-structured: it states the purpose, what the tool does, the argument, and the return value. Every sentence adds value without redundancy. It is efficiently written 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?

  The description covers the essential aspects: what the tool does, what input it expects, and what output it provides. For a simple guidance tool, this is sufficient. However, it could be slightly more complete by mentioning the format of the instructions (e.g., are they textual steps, API endpoints, etc.), but given the low complexity, the current level of detail is adequate.

  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?

  The single parameter 'organism' is described as 'Organism name (e.g., 'Homo sapiens', 'E. coli')', providing clear meaning and examples. The schema only specifies type as string, but the description adds concrete usage and format, which helps the user understand what to supply. This is better than just the bare schema.

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

  Purpose4/5

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

  The description clearly states the tool's purpose: to provide guidance on how to search for PDB entries by organism. It uses a specific verb ('get information') and identifies the resource (PDB entries by organism). However, it does not explicitly distinguish itself from sibling tools like 'query_rcsb_api' or 'get_pdb_entry', which might cause some ambiguity about when to use this tool versus those.

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

  Usage Guidelines2/5

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

  The description does not provide explicit guidance on when to use this tool versus alternatives. It only states that it provides guidance on using the RCSB search API, but does not mention any conditions or scenarios where this tool is preferred over the sibling tools. Users are left to infer when they should invoke this tool instead of others.

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

• get_polymer_entityA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the behavioral disclosure burden. It clearly states the output is a JSON string and lists the returned fields, which implies a read-only operation. However, it does not mention error behavior, invalid PDB IDs, not-found cases, or any API/network dependencies.

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

  Conciseness4/5

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

  The description is well-structured with purpose, Args, and Returns sections, and the bullet list of return fields is useful. It is slightly verbose but contains no filler or redundant 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?

  The description covers the essential invocation details: parameter formats, default value, and return content. Since an output schema exists, the explicit return list is a bonus. It does not address edge cases or failure modes, but they are not critical for basic correct use.

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

  Parameters5/5

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

  Schema description coverage is 0%, but the description fully compensates by explaining pdb_id's 4-character format with an example and entity_id's role with its default value. Both parameters receive meaningful semantic context beyond the bare 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 and resource: 'Get information about a polymer entity (protein, DNA, RNA) within a PDB entry.' This clearly distinguishes the tool from entry-level, download, query, and search siblings, even though it does not name them explicitly.

  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 the tool is for retrieving polymer entity details, but it provides no explicit guidance about when to choose it over siblings like get_pdb_entry or query_rcsb_api. No exclusions or alternative routing are given.

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

• download_structure_fileA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It states that the tool downloads a file and returns a JSON string with status and file path, and it explains the output_dir and filename parameters, implying file system writes. It does not mention potential side effects like overwriting existing files or network requirements, but these are reasonable assumptions for a download tool. The description is not contradictory and provides adequate transparency for safe invocation.

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

  Conciseness4/5

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

  The description is structured as a clear docstring with Args and Returns sections. It is not overly verbose, and each sentence provides necessary information. The main purpose is front-loaded, and the parameter details are organized logically. While it is longer than a one-liner, the detail is justified for the tool's functionality.

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

  Completeness4/5

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

  The description covers all parameters, provides return information, and explains file format options. It is complete for a download tool, and the existence of an output schema (not shown here) further reduces the need to describe return values in detail. It does not cover error handling or network prerequisites, but these are not essential for correct 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?

  The description comprehensively documents all four parameters in the Args section, exceeding the bare schema. It explains pdb_id as a 4-character PDB identifier with an example, enumerates all file_format options with defaults, and clarifies output_dir and filename defaults. Since schema coverage is 0%, the description fully compensates, adding significant meaning beyond the schema.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: 'Download a structure file from RCSB PDB.' This is a specific verb (download), resource (structure file), and source (RCSB PDB). It distinguishes from sibling tools like get_pdb_entry, which retrieve entry metadata, and query_rcsb_api, which performs API queries, by focusing on file download.

  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, nor does it mention exclusions or conditions. However, the purpose is self-evident for downloading structure files, and the existence of siblings for different tasks makes the usage context implicit. There is no misleading guidance, but the lack of explicit routing to alternatives is a gap.

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

• get_pdb_entryA
  4.4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden of disclosure. It transparently states the return format as a JSON string and enumerates the included fields, which is strong for a read-only lookup. It does not mention error handling for invalid IDs or network behavior, but those are minor for this kind of 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?

  The description is compact, front-loaded, and scannable, with an Args/Returns structure and a bullet list of returned information. Every sentence earns its place.

  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 single-parameter entry lookup with an output schema available, the description covers the input format and the return contents. Nothing essential for calling the tool correctly is missing, aside from sibling routing, which is a usage-guideline concern.

  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?

  The schema only declares pdb_id as a string, but the description fully defines it as a 4-character PDB identifier with concrete examples ('1ABC', '7BQY'). This adds substantial meaning beyond the raw 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?

  States a specific operation ('Get comprehensive information') on a precise resource ('a PDB entry'), and the Returns list clarifies that it provides metadata rather than a file. This distinguishes it from siblings like download_structure_file and get_polymer_entity.

  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 intended use is implied by the phrase 'comprehensive information' and the listed return fields, but there is no explicit when-to-use/when-not-to-use guidance and no reference to sibling alternatives. An agent must infer that search_pdb_by_organism is for finding IDs and download_structure_file is for file retrieval.

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