Server Quality Checklist

Tool Scores

• get_analysis_not_foundA
  4.1/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It does disclose the return type (Dict {count, notFound}) and the dependency on a valid token, which is useful behavioral context. However, it does not explicitly state that it's a read-only operation, nor does it describe error handling or rate limits. The verb 'List' implies safety but does not make it 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?

  The description is a compact, well-structured docstring with Args and Returns sections. Every sentence conveys necessary information and there is no redundancy. It is appropriately sized given the tool's simplicity.

  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 core function, parameters, and return value, which is sufficient for a list-like tool without an output schema. However, it leaves ambiguity about what 'count' represents (total unmapped vs. page count) and doesn't detail the inner structure of 'notFound'. This is a minor gap, but overall the tool is well-described.

  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%, so the description is the sole source of parameter meaning. It explains each parameter: token's origin, page's zero-based numbering, and page_size's role as identifiers per page. This fully compensates for the lack of schema descriptions, adding significant value.

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

  Purpose5/5

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

  The description begins with 'List the submitted identifiers that did not map to any Reactome entity,' which is a specific verb (list) plus a clear resource and scope. It distinctly identifies what the tool does and is not tautological. The resource ('submitted identifiers that did not map') makes it stand out from sibling tools like get_analysis_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 states the token is 'returned by analyze_identifiers,' which provides a clear prerequisite and implies the tool is used after running an analysis. However, it does not explicitly say when not to use it or mention alternative tools. The guidance is present but not deeply prescriptive.

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

• list_top_level_pathwaysA
  4.2/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It reveals the return shape ('Dict {count, pathways}'), the top-level scope, and accepted species formats, but does not disclose potential errors, rate limits, or pagination behavior. This is acceptable for a simple read-only list tool but not richly transparent.

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

  Conciseness5/5

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

  The description is compact and well-structured, with a one-sentence purpose followed by concise Args and Returns sections. Every line adds useful information with no redundancy.

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

  Completeness4/5

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

  For a tool with one parameter and no output schema, the description covers the essential aspects: purpose, parameter format, and return shape. It does not discuss edge cases or error handling, but these are not critical for such a straightforward listing operation.

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

  Parameters4/5

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

  The input schema only provides the parameter title 'Species', with 0% schema description coverage. The description compensates by explaining that species can be given as a name ('Homo sapiens') or NCBI taxId ('9606'), adding meaningful format 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 states a specific verb ('List') and resource ('top-level pathways for a species'), and clarifies that these are 'the browser's entry points'. This distinguishes it from sibling tools like list_pathway_events, which operate on events within pathways.

  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 this is for listing top-level pathways for a species, giving a clear usage context. It does not explicitly mention alternatives or when not to use it, but the purpose is specific enough to guide selection.

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

• get_complex_subunitsA
  4.3/5.0
  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 and does well: it discloses the recursive traversal, the effect of exclude_structures, and the return format (Dict `{count, subunits}`). It stops short of mentioning potential performance/scale implications, but the core behavior is transparent.

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

  Conciseness5/5

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

  The description is compact and well organized: a one-line summary followed by Args and Returns sections. Every sentence adds value; no fluff or repetition.

  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 no output schema, the description adequately covers purpose, parameters, and return type. It could optionally explain the structure of the returned subunits or edge cases, but the current level of detail is sufficient for an agent to invoke it correctly.

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

  Parameters5/5

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

  The schema has zero descriptions for parameters, so the description fully compensates: it explains stable_id with a concrete example and clearly defines exclude_structures ('If True, omit structural sub-complexes'). This adds meaningful semantic context 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 a specific action ('List the subunits that constitute a complex') and adds the key recursive behavior, distinguishing it from sibling tools like get_event_participants. The example stable id further anchors the intent.

  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 is implied by the description ('list the subunits that constitute a complex'), but there is no explicit guidance on when to choose this tool over alternatives such as get_event_participants or get_entry. No exclusions or 'use this when' language is present.

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

• get_entriesA
  4.3/5.0
  Behavior3/5

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

  No annotations present, so the description carries the burden. It discloses the max 20 limit and the return format, but does not mention behavior for missing/invalid identifiers or ordering. It provides some context but not full behavioral disclosure.

  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 and well-structured with Args and Returns sections. Every sentence is informative, and the example is concise yet valuable.

  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 one parameter and no output schema, the description adequately covers input and output. The max 20 limit is a useful constraint. It could be more complete with error behavior or a note about usage vs. get_entry, but overall it is sufficient.

  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 0%, yet the description fully explains the stable_ids parameter: it can be a list or a comma/whitespace-separated string, with a concrete example. This adds significant value 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?

  Clearly states 'Batch-fetch records for several identifiers in one call (max 20)', using a specific verb and resource. This distinguishes it from sibling tools like get_entry (singular) and search.

  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?

  Implies usage for retrieving multiple records at once, and the max 20 limit is stated. However, it does not explicitly mention alternatives or exclusions, so it lacks a direct when/not comparison to get_entry or search.

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

• get_entryA
  4.3/5.0
  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 and does well: it discloses the size guard behavior (max_chars replacing large nested fields with summaries), the enhanced variant's query path, and the return shape when attribute is set. It does not mention auth or rate limits, but these are likely irrelevant for a public fetch. The description adds meaningful behavioral detail beyond simple 'fetch.'

  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 appropriately structured with a lead sentence, a scope/usage sentence, and separate Args and Returns sections. It is slightly longer than the absolute minimum but every sentence provides useful information, with no fluff or repetition.

  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 and a 4-parameter tool, the description is highly complete: it explains all parameters, the return format for both normal and attribute modes, the size guard, and the enhanced variant. It also covers the range of supported object types. There are no gaps left for the agent to guess.

  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 compensates fully by explaining each parameter: stable_id with an example, enhanced with its query variant, attribute with concrete examples, and max_chars with its size-guard behavior. This provides complete meaning that the input schema alone lacks.

  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 opens with a specific verb and resource: 'Fetch the full record for any Reactome object by identifier.' It explicitly lists supported entity types (pathways, reactions, physical entities, complexes, regulators) and distinguishes itself from siblings like get_entries (which is plural and likely batch-focused) and get_event_* tools by stating it handles any identifier.

  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 gives clear context on what object types it works for and offers parameter-level guidance ('Use attribute to retrieve a single field cheaply, or enhanced to include indirect references'). However, it does not explicitly state when to avoid this tool or compare it to alternatives like get_interactors or get_complex_subunits, leaving the when-to-use guidance implied rather than explicit.

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

• get_event_participantsA
  4.4/5.0
  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 the return format (Dict with count and participants), the grouping of PhysicalEntities with ReferenceEntities, and cross-reference types (UniProt/ChEBI). It lacks details on error handling or authentication needs, but for a read-only listing tool, this is reasonably transparent.

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

  Conciseness5/5

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

  The description is succinct and well-structured, with a clear purpose sentence followed by Args and Returns sections. Every line adds value, and there is no redundancy or 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 the tool's simplicity (one parameter, no output schema, no annotations), the description covers the essential aspects: purpose, parameter semantics, and return structure. It does not discuss edge cases or related tools, but for a straightforward lookup tool, it is sufficiently 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?

  The schema provides only the parameter name and title, with 0% description coverage. The description compensates by explaining that 'stable_id' is an 'Event stable id' and gives an example ('R-HSA-69620'). This adds meaning beyond the schema, though it could further clarify how to obtain such an ID.

  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 states a specific verb ('List') and resource ('physical entities that participate in a reaction or pathway'), making the tool's function clear. It effectively distinguishes itself from sibling tools like 'get_event_ancestors' or 'get_interactors' by focusing on event participants.

  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 the tool (when you need participants of a reaction/pathway) and provides a concrete example stable ID, giving clear context. However, it does not explicitly mention alternative tools or when not to use it, which would elevate it to a 5.

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

• download_exportA
  4.5/5.0
  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 discloses the write-to-disk side effect, directory creation ('created if absent'), and the error return format ('ERROR:'). It does not mention overwrite behavior or file naming, but covers the main 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?

  The description is front-loaded with the purpose, followed by usage guidance, then a structured Args list and Returns. It is concise and every sentence earns its place, with no wasted words.

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

  Completeness4/5

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

  For a download tool with 4 parameters and no annotations, the description is thorough: purpose, usage, parameter semantics, and return format. Minor gaps like overwrite behavior and exact file naming remain, but it is essentially complete.

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

  Parameters5/5

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

  Schema description coverage is 0%, but the Args section thoroughly explains each parameter: stable_id with fireworks naming, kind with valid values, ext validity for the chosen kind, and save_dir creation. This adds substantial meaning beyond the schema's titles/defaults.

  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 states 'Stream a Reactome export to local disk and return the absolute path', which is a specific verb+resource+outcome. It distinguishes from siblings by mentioning use for non-trivial payloads and listing format types (SBML/SBGN, PDF, diagram images), clearly setting it apart from tools that return content directly.

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

  Usage Guidelines4/5

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

  It explicitly says 'Use this for any non-trivial payload ... instead of pulling it into the chat', providing clear when-to-use context. However, it does not name specific alternative tools or state when-not-to-use, so it stops short of full alternatives/ exclusions guidance.

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

• get_analysis_resultsA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description must carry the behavioral burden. It does so with a non-destructive verb ('Retrieve'), explicit paging/sorting/filtering behavior, and a note that the return shape matches analyze_identifiers. It doesn't mention edge cases like token expiration or error handling, but for a read-only retrieval tool this 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?

  The description is well-structured with a one-sentence summary followed by a compact Args and Returns list. Every sentence adds value, and there is no redundant repetition of schema 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?

  All parameters are described, and the return shape is addressed via cross-reference to analyze_identifiers. However, it relies on the agent already knowing analyze_identifiers' return schema and doesn't mention potential error states or result availability, which is a minor gap for such a parameter-rich tool.

  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 0%, so the description fully compensates by explaining all 7 parameters with meaningful detail, including concrete examples for sort_by (ENTITIES_PVALUE, ENTITIES_FDR) and the exact meaning of p_value. This is far more useful than the bare schema titles and defaults.

  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 begins with a clear verb ('Retrieve') and names the resource ('results of a prior analysis'), with an explicit dependency on the token from analyze_identifiers. The parenthetical '(page/sort/filter)' conveys the tool's scope, which helps distinguish it from the many 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?

  It clearly establishes when to use this tool: after a prior analysis has been performed, with a token returned by analyze_identifiers. It doesn't explicitly list alternative tools or when not to use it, but the context is unambiguous and no alternatives are truly competing for this exact task.

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

• get_interactorsA
  4.5/5.0
  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. It discloses the return format (interactor summary object with accessions and scores) and the -1 default behavior for pagination parameters. It doesn't mention error cases, but it is transparent about the core behavior.

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

  Conciseness5/5

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

  The description is concise and well-structured: a one-line summary followed by Args and Returns sections. Every sentence provides useful information, and there is no redundancy or 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?

  For a simple read tool with no output schema, the description covers the essential behavior, parameters, and return format. It could add details about edge cases (e.g., empty results), but it gives enough context for correct selection and 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 0%, so the description must explain the parameters. It does so thoroughly: 'accession: A UniProt/ChEBI accession', 'page: 1-based page number; -1 (default) returns all', and 'page_size: Page size; -1 (default) returns all'. This fully compensates for the schema's lack of descriptions.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: 'Fetch curated protein-protein interactors for an accession (IntAct)'. It uses a specific verb ('fetch') and resource ('protein-protein interactors'), and differentiates from siblings like get_event_participants by specifying IntAct and protein-protein interactors.

  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 gives clear context: use this tool to retrieve interactors for a given UniProt/ChEBI accession, with pagination options. It does not explicitly name alternatives or exclusions, but the use case is clearly implied.

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

• list_diseasesA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the transparency burden. It discloses the return format (Dict with count and diseases) and data source (Disease Ontology terms), which is appropriate for a non-mutating list 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 two sentences, front-loaded with the main action, and includes only essential return information without 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?

  For a simple parameterless list tool, the description sufficiently explains what the tool returns and from where, making it contextually 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?

  The tool takes no parameters, so the schema is complete and description adds no parameter semantics needed. The baseline for zero-parameter tools 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 uses a clear verb 'List' and specifies the resource 'diseases annotated in Reactome', which distinguishes it from sibling list tools like list_species and list_top_level_pathways.

  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 states this returns diseases from Reactome, providing clear context for when to use it. It does not explicitly mention alternatives, but the context is sufficient for an agent to recognize this as the disease list tool.

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

• list_pathway_eventsA
  4.5/5.0
  Behavior5/5

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

  With no annotations, the description fully carries the burden of behavioral disclosure. It explicitly discloses the recursion of the full sub-tree and the flattened result set, which are key behavioral traits beyond the basic 'list' 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 efficiently structured: a clear one-sentence summary, followed by Args and Returns sections. Each sentence adds value, and there is no fluff or 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 the tool's moderate complexity and lack of output schema, the description still specifies the return dictionary format ({count, events}) and the recursive behavior. This provides sufficient context for an agent to invoke the tool and interpret results.

  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 0%, but the description compensates by defining stable_id as a 'Pathway stable id' and providing an example ('R-HSA-69278'). This adds semantic meaning beyond the schema's plain string type, though it could offer more detail on acceptable formats.

  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 every event (sub-pathway and reaction) in a pathway, using a specific verb and resource. It distinguishes itself by noting it recurses the full sub-tree, unlike sibling tools that might handle top-level or ancestor queries.

  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 use case (flatten all events below a pathway) but does not explicitly mention when to prefer it over alternatives or exclude other tools. There is no direct comparison with siblings like get_event_ancestors or get_event_participants.

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

• get_event_ancestorsA
  4.6/5.0
  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 the return structure (a dict with 'count' and 'ancestors') and clarifies that ancestors are ordered paths. While it does not cover edge cases like invalid IDs, the behavior is straightforward and well-explained for a read-only retrieval.

  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 and well-structured with clear Args and Returns sections. It states the core purpose in one sentence, followed by the parameter explanation and return format—no redundant or extraneous content.

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

  Completeness5/5

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

  Given the tool's simplicity (one required parameter, no output schema), the description provides complete contextual information: what it does, what the parameter means, and what the response will contain. The agent has everything needed to invoke it correctly.

  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 defines 'stable_id' as a string with no description. The tool description adds essential meaning: that it is an 'Event (pathway or reaction) stable id' and provides a concrete example ('R-HSA-69620'). This fully compensates for the 0% 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 states a specific verb ('Retrieve') and resource ('all paths from an event up to its top-level pathway(s)'), clearly distinguishing it from sibling tools like get_event_participants or find_pathways_for_entity. The breadcrumb use case further clarifies its unique role.

  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 notes it is 'Useful for building breadcrumbs / locating where a reaction sits', providing a clear use case. It does not explicitly mention when not to use it or direct to alternatives, but the context is sufficient for the agent to select it appropriately.

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

• list_speciesA
  4.6/5.0
  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 discloses the default behavior of main_only (returning only curated species) and the alternative (including computational inferences). It also states the return structure, giving the agent a clear picture of what to expect.

  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 and well-structured with clear Args and Returns sections. Every sentence adds value, with no fluff or 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?

  For a simple read-only tool with one optional parameter, the description covers the purpose, parameter behavior, and return format. No output schema is provided, but the description fills that gap adequately. It is complete for the tool's complexity.

  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 input schema only provides the property name, type, and default with no description. The tool description compensates fully by explaining exactly what main_only=True vs False does, 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 starts with 'List the species annotated in Reactome', which is a specific verb+resource statement. It clearly distinguishes from sibling tools like list_diseases and list_top_level_pathways by focusing on species.

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

  Usage Guidelines4/5

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

  The description provides clear context that this tool lists species and explains the main_only parameter's effect. It doesn't explicitly mention alternatives or when-not-to-use, but the purpose is unambiguous and the context is clear enough for an agent to select it appropriately.

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

• searchA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden and does well: it reveals the Solr backend, return structure (entries, entriesCount, resultTypes), that HTML markup is stripped, and that 'cluster' groups hits by type. It does not mention errors, rate limits, or default sorting, but the core behavior is well disclosed.

  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 front-loaded with a one-sentence summary, followed by a tightly structured Args list and a Returns explanation. Every sentence is informative and necessary; no filler or repetition. The length is appropriate for the tool's complexity.

  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 that there is no output schema and no annotations, the description covers the tool's purpose, all parameters, return structure, and behavioral nuances. It is sufficiently complete for an agent to select and invoke the tool correctly, including pagination and response compaction.

  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 has zero descriptions for parameters, and the description fully compensates by explaining each parameter (query, species, types, rows, start, cluster) with examples and formatting expectations. It adds meaning beyond the bare schema, clarifying value ranges, defaults, and effects such as clustering.

  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 a specific action ('Free-text search') applied to a defined resource ('the Reactome knowledgebase'), and further specifies what is matched (pathways, reactions, physical entities, reference molecules) and by which criteria (name, synonym, identifier, cross-reference). This clearly distinguishes it from sibling tools that handle specific lookups or listings.

  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 gives clear context for when to use the tool (general free-text searching across multiple entity types) with illustrative query examples. It does not explicitly mention alternatives or state when not to use it, but the scope is evident from the text. This matches 'clear context, no exclusions'.

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

• analyze_identifiersA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden and delivers richly. It discloses that identifiers are submitted to an external service, explains the projection behavior, lists all filtering and pagination options, and details the return structure including token, warnings, and identifiersNotFound. This goes beyond minimal disclosure and sets clear expectations.

  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 a strong opening summary, an Args list, and a Returns block. It is somewhat long due to the detailed parameter explanations, but every sentence earns its place given the 8 parameters and missing annotations. The front-loaded purpose sentence ensures immediate clarity.

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

  Completeness5/5

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

  Given the tool's complexity (8 parameters, no annotations, no output schema), the description is exceptionally complete. It explains the full request/response lifecycle, including token-based pagination, and provides the exact shape of the returned dict. This makes the tool usable without any external documentation.

  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%, so the description must compensate for all 8 parameters, and it does. Every parameter (identifiers, projection, species, sort_by, p_value, page_size, page, include_interactors) receives a meaningful explanation with types, defaults, and examples. This fully overcomes the schema's lack of descriptions.

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

  Purpose5/5

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

  The description opens with a specific verb and resource: 'Run pathway over-representation analysis on a gene/protein list.' It clearly states the function and distinguishes itself from siblings like get_analysis_results, which retrieves previously submitted analyses, by emphasizing submission to Reactome and returning a token for later reuse.

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

  Usage Guidelines4/5

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

  The description provides clear usage context: it explains submission to the Reactome AnalysisService and explicitly directs users to 'Reuse the returned token with get_analysis_results to page/sort/filter without re-submitting.' This names an alternative tool and implies when to use each, though it does not include an explicit 'when not to use' list.

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

• find_pathways_for_entityA
  4.7/5.0
  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. It discloses the query nature ('Find...'), the return structure ('Dict {count, pathways} of Pathway records'), and the optional behavior of `all_forms` ('also match every other form'). It does not explicitly state read-only behavior, but the wording strongly implies a non-mutating search.

  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 and well-structured. It opens with the core purpose in one sentence, then provides a clear Args/Returns breakdown. Every sentence adds value, and there is no redundant fluff or repetition of schema 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 moderate complexity (3 parameters, no output schema, no annotations), the description covers the essential context: purpose, relationship to a sibling tool, parameter meanings, and return format. It doesn't enumerate possible error conditions or elaborate on what constitutes a 'Pathway record,' but those are not critical for a query tool of this nature.

  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%, so the description must compensate. It does so thoroughly: `stable_id` is given with an example ('R-HSA-199420'), `species` is explained as an optional name/taxId filter, and `all_forms` is defined with the behavioral effect ('match every other form of the entity'). This adds meaning well beyond the bare property titles.

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

  Purpose5/5

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

  The description clearly states the tool's function: 'Find the lower-level pathways that contain a given physical entity.' It uses a specific verb ('find'), a clear resource ('pathways'), and an explicit entity type ('physical entity'). It also distinguishes itself from the sibling tool `list_pathway_events` by calling itself the 'inverse' of that tool.

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

  Usage Guidelines5/5

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

  The description explicitly identifies when to use this tool: 'given a molecule/complex, which pathways involve it?' It also names the related alternative `list_pathway_events` and states the inverse relationship, giving the agent clear context for selecting this tool over its sibling.

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

• get_event_sbmlA
  5/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden. It discloses truncation behavior, return format, and the safety guarantee that multi-MB XML never floods the chat. This is thorough and transparent.

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

  Conciseness5/5

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

  The description is well-structured, front-loaded with a clear summary, followed by a brief rationale and then concise parameter and return details. Every sentence adds value; no redundancy or filler.

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

  Completeness5/5

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

  Given the tool's moderate complexity and lack of output schema, the description is complete. It covers the full return structure, truncation behavior, and the relationship to `download_export`, leaving no major gaps for invocation.

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

  Parameters5/5

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

  The schema provides zero parameter descriptions, and the description fully compensates. Each parameter (`stable_id`, `fmt`, `max_chars`) is explained with examples, defaults, and semantics, far exceeding what the schema alone offers.

  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 exports a pathway/reaction to SBML or SBGN, with a specific verb and resource. It distinguishes itself from the sibling tool `download_export` by explicitly mentioning size guarding and truncation, making its scope unambiguous.

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

  Usage Guidelines5/5

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

  It explains when to use this tool (inline export for systems biology) and explicitly points to `download_export` for large exports that exceed inline limits. This provides an explicit alternative and contextualizes usage.

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