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

With no annotations, the description must disclose behavioral traits. It mentions capping and redirection to export_snippet, which is useful. However, it omits critical details such as whether the tool is read-only, performance characteristics, or how results are truncated. The single behavioral disclosure is insufficient.

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

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

The description is extremely short (two fragments) and lacks structure. While it is concise, it sacrifices essential information. Important details are missing, making it too minimal for an agent to use effectively.

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

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

Given the tool's complexity—nested filter objects, multiple parameters, no output schema—the description is severely incomplete. It does not explain filtering logic, available aggregations, grouping options, output format, or the capping threshold. An agent cannot infer correct usage from this description alone.

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

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

The input schema has 0% description coverage and four top-level parameters (filters, gene_ids, group_by, aggregations), all with nested structures. The description fails to explain any of these parameters, their purposes, or how they influence results. It adds no semantic value beyond the schema itself.

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

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

The description states 'Per-gene expression stats by group' which clearly indicates aggregation of gene expression data across groups. The reference to 'caps → export_snippet if over' hints at a truncation behavior. However, it does not explicitly differentiate from sibling tools like census_summary or gene_coverage, which may also compute statistics.

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

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

The description provides no guidance on when to use this tool versus alternatives. It mentions a fallback to export_snippet but does not specify prerequisites, conditions for capping, or scenarios where other tools would be more appropriate.

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

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

No annotations are provided, so the description must fully disclose behavior. It only lists what is returned (cells, schema, build date), but omits whether it is read-only, requires authentication, or has any side effects. The brief description provides minimal behavioral context.

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

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

The description is extremely concise, consisting of a single sentence. It is front-loaded with the key output elements. However, it could include a bit more context without sacrificing conciseness, such as the purpose or format.

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

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

Given no input parameters, no output schema, and a simple description, the tool is minimally adequate. However, it lacks details on the return format, how the summary is structured, and how it relates to sibling tools. This leaves gaps for an AI agent to infer correctly.

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

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

The tool has no parameters, and the input schema coverage is 100%. The description correctly implies no input is needed. Since there are no parameters to elaborate, the baseline score of 4 applies.

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

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

The description states it returns a 'Census summary: cells, schema, build date,' which indicates a retrieval of basic metadata. However, the term 'Pinned Census' is ambiguous, and the action (e.g., 'get' or 'retrieve') is implied rather than explicit. It partly distinguishes from siblings by focusing on summary, but not clearly enough.

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

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

There is no guidance on when to use this tool versus alternatives like 'get_census_versions' or 'count_cells'. The description does not specify prerequisites, contexts, or exclusions.

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

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

No annotations are provided, and the description does not disclose behavioral aspects such as whether the operation is read-only, performance characteristics, or any side effects. The term 'tier 0' is cryptic and does not clarify behavior.

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

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

The description is extremely concise, but it sacrifices necessary detail. It front-loads the core idea but omits important context, making it minimally adequate.

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

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

Given the complex input schema with many nested filter objects and no output schema, the description is severely incomplete. It does not address the variety of filter options or how results are returned, leaving significant gaps for an agent to interpret correctly.

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

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

The description merely lists parameter names ('filters', 'group_by') without explaining their semantics or usage. With 0% schema description coverage, the agent gains no additional insight beyond the property names, which is insufficient for correct invocation.

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

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

The description clearly states the tool counts cells and mentions the key parameters (filters, optional group_by). The verb 'Count' and resource 'cells' are specific, and the functionality is distinct from sibling tools like list_datasets or gene_coverage.

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

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

The description provides no guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or exclusions. The agent must infer usage from the tool name alone.

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

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It mentions 'filtered to Census presence' but does not explain what that implies (e.g., whether it modifies the expansion or filters results). There is no indication of read-only or destructive behavior, rate limits, or side effects, which is critical for a tool with 5 parameters.

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

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

The description is a single sentence, which is concise but not structured. It lacks readability enhancements (e.g., bullet points) for a tool with 5 parameters. The sentence is front-loaded with the core action, but the brevity sacrifices completeness for conciseness.

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

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

Given 5 parameters, no output schema, and no annotations, the description is woefully incomplete. It fails to explain the purpose of each parameter, the expected output format, or any side effects. The tool's complexity demands a more detailed description to be usable by an AI agent.

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

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

With 0% schema description coverage, the description adds no meaning beyond the raw schema. Parameters like 'facet' and 'include_counts' are unexplained, and the role of 'direction' is only implied by the enum values. The default values alone do not clarify semantic intent.

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

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

The description clearly states the action ('expand'), the resource ('CURIE'), and the specific context ('descendants/ancestors filtered to Census presence'). This distinguishes it from siblings like 'resolve_term', which likely returns a single definition. However, 'Census presence' is not immediately clear without domain knowledge, preventing a perfect score.

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

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

No guidance is given on when to use this tool versus alternatives like 'resolve_term' or 'term_definition'. The description does not mention typical use cases, conditions, or exclusions, leaving the agent to infer usage from context alone.

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

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

No annotations are provided, so the description must disclose behavioral traits. It mentions 'Runnable Python' hinting at code execution, but does not confirm whether the tool is read-only or destructive, or describe any side effects, authentication needs, or rate limits.

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

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

The description is a single sentence, which is concise, but it is under-specified and fails to provide necessary information. It is not effectively front-loaded with key details.

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

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

Given the lack of output schema and annotations, the description should compensate but does not explain what the tool returns, its side effects, or how to correctly use the parameters. Context is incomplete for effective usage.

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

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

Schema description coverage is 0% and the description only mentions call_id, ignoring the intent parameter entirely. The description adds no meaning beyond the schema, which already provides enum choices for intent. For a tool with 2 parameters, this is insufficient.

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

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

The description states 'Runnable Python for a stored plan' and mentions passing a call_id from a prior response, which gives a general idea of executing a stored plan. However, it does not specify what 'export' means in terms of output or how it differs from siblings like 'aggregate_expression' or 'count_cells'.

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

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

The description implies that the tool should be used after obtaining a call_id from a prior response, but it does not provide explicit guidance on when to use this tool versus alternatives, or state any prerequisites or conditions.

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

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

No annotations provided. Description only says 'Report whether... present', implying a boolean output but does not disclose error handling, rate limits, authentication needs, or side effects. Minimal 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.

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

Description is very concise at 12 words, but this brevity sacrifices necessary detail. It is not front-loaded with key information beyond the basic purpose.

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

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

No output schema, no annotations, and no explanation of the result format. The tool's behavior with multiple gene IDs or edge cases is unclear. Incomplete for effective use.

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

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

Schema description coverage is 0%, yet description does not mention or explain either parameter (gene_ids or organism). Parameters are left entirely undocumented for the agent.

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

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

Description clearly states the tool reports presence of Ensembl gene IDs in Census var. Verb 'Report' is acceptable, and resource is specific. However, 'Census var' is ambiguous and not explained.

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

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

No guidance on when to use this tool versus siblings like census_summary or list_available_values. No context about prerequisites or typical use cases.

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

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

With no annotations, the description must disclose behavioral traits but only says 'visible to this server'. It omits details like whether it's read-only, cached, or requires authentication.

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

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

A single sentence that efficiently conveys the tool's purpose without unnecessary words.

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

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

Given no parameters, no output schema, and a simple purpose, the description is mostly complete but could briefly mention what the listing returns (e.g., version strings).

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

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

There are zero parameters, so schema coverage is 100%. The description adds no param info, which is acceptable; baseline is 4.

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

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

The description clearly states the verb 'List' and the resource 'Census versions', and it distinguishes from sibling tools (e.g., aggregate_expression) which focus on data operations.

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

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

The description implies usage when one needs to know available versions, but it provides no explicit guidance on when to use this tool vs alternatives or any conditions for use.

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

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

No annotations are provided, so the description must fully disclose behavior. It implies a read-only, non-destructive operation ('Report'), but offers no details on response format, potential errors, rate limits, or whether any side effects exist.

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

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

The description is a single, clear sentence with no wasted words. It immediately conveys the tool's function and rationale, making it easy for an agent to parse quickly.

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

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

Given no parameters, no annotations, and no output schema, the description is adequate but minimal. It tells the agent the tool reports configuration limits, but lacks specifics on what fields or constraints are included, which could lead to under- or overestimation of its capabilities.

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

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

There are zero parameters, so schema coverage is trivially 100%. The description adds value by explaining the tool's purpose, which is essential given the empty schema. A baseline of 4 is appropriate as the description compensates for the lack of parameter details.

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

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

The description uses a specific action verb ('Report') and resource ('cap configuration') with a clear rationale ('so clients can size their requests'). It distinguishes itself from sibling tools like 'aggregate_expression' or 'census_summary' by focusing on server limits rather than data exploration.

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

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

No guidance is provided on when to use this tool versus alternatives, nor any conditions or prerequisites. The description does not mention when it would be inappropriate or what the tool does not do.

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

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

No annotations provided, so description must cover behavioral traits. It only states it lists distinct values, implying a read operation, but misses details like performance limits, error conditions, or any 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.

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

Single sentence with front-loaded purpose and a contextual hint. Efficient but risks being too terse for agents unfamiliar with the domain.

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

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

No output schema, no annotations, and incomplete parameter semantics. The description omits return format, pagination, error handling, and the relationship to the 'obs' concept. Lacks completeness for reliable invocation.

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

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

Schema description coverage is 0%, and the description adds no information about what parameters like 'column', 'organism', 'prefix', or 'limit' mean. Agent fully reliant on schema types, which are insufficient.

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

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

Clearly states it returns distinct values for an obs column, and the parenthetical 'discovery before resolve_term' provides context on its role in a workflow. However, 'obs column' is jargon that may not be immediately clear to all agents.

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

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

Implies usage before resolve_term, but does not explicitly state when to use this tool vs siblings like expand_term or term_definition. No guidance on when not to use it.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only mentions sorting by cell count, omitting information about read-only nature, pagination, response format, or any 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.

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

While extremely concise, the description is under-specified for the tool's complexity. It fails to earn its place by omitting critical context, making it more of a vague statement than an informative guide.

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

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

Given the nested input schema, no output schema, and many sibling tools, the description is incomplete. It does not explain what a structured filter entails or how to construct it, leaving the agent under-informed for successful invocation.

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

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

Schema description coverage is 0%, yet the description adds no parameter-level details. 'Structured filter' is vague and does not clarify the complex nested schema, leaving the agent to infer parameter usage from the schema alone.

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

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

The description clearly states the action ('List datasets'), the resource ('datasets'), and key details ('matching a structured filter, sorted by cell count'). It effectively distinguishes the tool from siblings like count_cells and aggregate_expression by focusing on listing with sorting.

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

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

The description gives no guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or exclusions. It provides no context about when not to use it.

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

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

No annotations are provided, so the description must fully disclose behavioral traits. It mentions 'preview' hinting at a read operation, but does not specify side effects, permissions, rate limits, or what happens to data. Lacks explicit behavioral details.

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

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

The description is very short (one phrase), which is concise but omits essential information. It is appropriately sized for a quick overview but could benefit from a few more details.

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

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

Given the complex input schema with nested objects and no output schema, the description is severely incomplete. It does not define 'obs', explain the output format, or elaborate on cardinality, leaving agents uninformed.

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

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

The description mentions 'slice' and 'cardinality', loosely relating to filters and limit parameters, but does not clarify their meaning or usage. With 0% schema description coverage, the description fails to compensate adequately.

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

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

The description 'Small obs slice + column cardinality (before a big scan)' conveys the tool's purpose as a preview tool for a small slice of observations and column cardinality, distinguishing it from siblings like count_cells or gene_coverage. However, it relies on domain jargon and could be more explicit.

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

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

The phrase 'before a big scan' implies usage for quick checks prior to larger operations, but no explicit when-to-use or when-not-to-use guidance is provided, nor are alternatives mentioned.

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

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

No annotations provided, so description carries full burden. Mentions 'typed refusal if ambiguous' but does not disclose error handling, missing term behavior, or other 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.

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

Single sentence is concise but omits critical parameter details, making it insufficient despite being front-loaded.

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

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

With 4 parameters, no output schema, and no annotations, the description is incomplete. It does not cover behavior for various inputs or return format.

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

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

Schema coverage is 0%. Description only mentions 'text or CURIE', leaving ontology, facet, and confirm_ambiguous parameters completely unexplained.

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

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

Clearly states it resolves text or CURIE to a single term, with a specific behavior for ambiguity. Distinguishes from siblings like expand_term and term_definition.

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

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

No explicit guidance on when to use this tool vs alternatives. Does not mention prerequisites or contexts where other tools are preferred.

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

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

No annotations provided, so description carries full burden. It states what is returned but omits details like error handling (e.g., invalid CURIE), output format, or any side effects. Adequate for a simple lookup but could be more transparent.

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

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

One concise sentence (6 words) conveying the tool's purpose with no redundancy.

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

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

Absence of output schema and annotations leaves gaps. The description does not cover return structure or edge cases, but the tool's simplicity partly compensates.

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

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

Single parameter 'curie' is described as 'a CURIE' but lacks format examples or constraints. With 0% schema description coverage, the description adds minimal beyond the schema.

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

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

Description explicitly states the tool returns label, definition, synonyms, and IRI for a CURIE. It clearly identifies the resource and action, distinguishing from similar tools like 'resolve_term' or 'expand_term'.

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

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

No explicit guidance on when to use this tool versus siblings like 'resolve_term' or 'expand_term'. The context is implied but not clarified.

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