GrantIQ

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

With no annotations, the description carries the full burden. It discloses partial-update semantics (null fields unchanged) and server-side filtering of beneficiary/mission tags. Permission or rate limit details are absent but not critical for this tool.

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 concise with two information-dense sentences. It is front-loaded with purpose and efficiently covers key points. A slightly more structured format could improve readability, but it is not wasteful.

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 output schema and 15 nested parameters, the description covers purpose, update semantics, filtering, and next steps. It lacks error handling or return value format beyond saved=true, but is adequate for a profile update tool.

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%, so the description must compensate. While it explains partial updates and filtering, it does not elaborate on individual parameter meanings. The field names are self-explanatory, but more context would help for complex fields like research_interests.

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 fills in the user's matching profile field-by-field via chat. The verb 'fills in' and resource 'matching profile' are specific, and the sibling context distinguishes it by recommending find_opportunities after completion.

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 explicitly tells the agent to call find_opportunities after saved=true, providing clear next-step guidance. It implies this tool is for completing the profile before searching, but lacks explicit when-not or alternative tools.

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 effectively discloses caching behavior and sub-50ms performance. It implies read-only semantics but does not explicitly state no side effects. The caching detail adds transparency.

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?

Three sentences, each valuable: purpose, output list, caching performance. Front-loaded and no wasted 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 the single parameter, no output schema, and no annotations, the description thoroughly covers what the tool returns (summary, constraints, mechanics, etc.), prerequisites, and performance characteristics. No gaps.

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 100% for the single parameter with a clear description in the schema. The tool description adds no additional meaning beyond reiterating the parameter's purpose. Baseline 3 is appropriate.

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 specifies a clear action ('plain-English unpack of a single grant') and resource, listing exact outputs. It implicitly differentiates from sibling tools like find_opportunities (search) and should_apply (decision) by focusing on explanation of a single grant.

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 mentions that the grant_id is typically from a prior search or find_opportunities call, providing context for when to use. However, it does not explicitly state when not to use or compare to alternatives.

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 the burden. Discloses that 'not found' is returned for both unknown and not visible grants, with no information leak. Adequate for a simple fetch tool.

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?

Two sentences, no redundant information. Every sentence adds value: first states purpose, second clarifies provenance of id and edge case behavior.

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 single required parameter and no output schema, description fully covers what the tool does, how to use it (id from search), and return behavior ('not found' cases). No gaps.

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 100%, baseline 3. Description adds that id must be from prior search, consistent with schema. No additional semantic nuance beyond 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?

Clearly states it returns full record for a single grant by id, and specifies id must come from prior `search` call. Differentiates from sibling `search` and other tools.

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?

Explicitly says id must come from a prior `search` call, guiding when to use. Also describes 'not found' behavior but doesn't explicitly list alternatives or when not to use beyond that.

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 the description carries the full burden. It mentions using a canonical StagedMatchingService and requires a complete profile, but does not disclose whether the operation is read-only, any side effects, rate limits, or error scenarios.

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 two sentences with no wasted words. Key information is front-loaded (tool name and action), and every sentence adds value.

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?

The tool is simple (one param, no output schema, no nested objects), but the description omits any hint about the return format or error handling. It covers the prerequisite well but is incomplete for an agent to fully understand what the tool returns or how to handle empty results.

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 100% with a single 'limit' parameter described as maximum results. The description adds no additional meaning beyond what the schema already provides, so baseline 3 is appropriate.

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's action: running the user's profile through an AI matching engine to find top grants. It uses a specific verb ('runs') and resource ('user's profile'), distinguishing it from siblings like 'search' or 'explain_opportunity'.

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 explicitly states a prerequisite: requires a complete profile (Location, OrgType, etc.), implicitly guiding when to use vs when to use 'complete_profile'. However, it does not explicitly mention alternative tools or 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 carries the full burden. It discloses that results are limited to currently-open, AI-enriched grants and that closed/suspended/unpublishable rows are never returned. This provides meaningful behavioral context beyond schema.

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, front-loaded sentence that covers purpose, usage hint, and constraints. Every part is necessary; no wasted 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 the simple tool (2 params, no output schema), the description explains what fields are returned (id, title, funder, deadline, amounts) and what is excluded, making it self-contained for an 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?

Schema coverage is 100%, so the description does not need to add much. It confirms that 'query' matches title, summary, and description, and 'limit' defaults to 10. This adds marginal value over the schema, earning a baseline 3.

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 'find UK & EU grants matching a free-text query', specifying the verb 'find' and resource 'grants'. It distinguishes from sibling 'fetch' by noting that this tool returns a ranked list of grant references for later retrieval.

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 explicitly mentions that results can be passed to the 'fetch' tool for full detail, guiding workflow. It also clarifies that only open, AI-enriched grants are returned, implying when not to use (for closed grants). No explicit when-not-to-use for other scenarios, hence 4.

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 the description carries full burden. It discloses that it returns a verdict, confidence, blockers, effort estimate, competition risk, and evidence. However, it does not mention behavioral aspects such as whether it is a read-only operation, rate limits, or error conditions.

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 concise: one sentence for purpose, one sentence listing outputs, and one sentence for prerequisite. It is front-loaded and every sentence adds value with no wasted 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 the tool's complexity (returns multiple structured fields) and no output schema, the description adequately explains all return values. It also covers the prerequisite. Missing details like error handling or behavior when profile is missing, but overall sufficient for an agent to use 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 single parameter 'grant_id' has schema description stating it is a UUID from prior searches. The description adds context: 'Typically returned in a prior search or find_opportunities call.' This clarifies provenance and usage 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?

The description clearly states it provides an opinionated apply/don't-apply decision for a grant, listing specific outputs (verdict, confidence, blockers, etc.). It distinguishes from siblings like 'find_opportunities' which returns grants, not evaluations.

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 explicitly states the prerequisite: caller's profile must be set via prior 'find_opportunities' or web sign-up. This guides when to use the tool. It does not explicitly exclude alternatives, but the context implies it is for evaluation after profile setup.

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