GrantCue

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description goes beyond them with useful limits: it never returns the full list of reported grants, Form 990 filers expose only top 10 recipients and yearly totals, and no-application-info exists for 990 filers. It does not say what happens when the EIN has no profile (error vs. empty result), which would have earned a 5.

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 content is dense but front-loaded with the resource identity and follows with the 990-PF/990 split; every clause carries information. The first sentence is unusually long and packs the full return manifest, which slightly hurts scanability but not comprehension.

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 exists, and the description compensates by enumerating returned fields and negative guarantees (no full grant list). With one parameter at full schema coverage and read-only annotations, the only meaningful omission is failure behavior for an EIN without a qualifying return.

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% and the single EIN parameter is fully documented with a pattern and note that the dash is optional, so the schema carries the load. The description adds no EIN-specific guidance (e.g., where to source the EIN) beyond implying the lookup is on public-profile foundations.

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?

Names a specific verb/resource (a foundation's public GrantCue profile) and enumerates exactly what it returns: giving totals, median grant, giving by year, geography, 25 largest grants, plus how to apply for 990-PF filers. It is clearly distinguishable from get_grant, search_funders, and search_grants because it is a single-entity detail fetch keyed by EIN.

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?

Gives explicit coverage conditions (only foundations with a public profile, or funders with a Schedule I return, are found) and explains the 990-PF vs Form 990 branch, including that Form 990 never states whether applications are accepted. It stops short of stating the complementary workflow — e.g., use search_funders to obtain an EIN before calling this — so a small inference gap remains.

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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds the non-obvious negative case that non-public grants return nothing. It does not describe error shape or whether a partial record can be returned, but the key behavioral trap (hidden grants silently absent) is disclosed.

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 short sentences, front-loaded with what is returned, no redundant restatement of the title. Every clause carries information.

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 no output schema, the description usefully enumerates the returned content (dates, amounts, eligibility, funder links) and covers the not-found case. It could say more about what happens when the id is malformed versus when the grant is private, but nothing essential to correct invocation is missing.

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 is a single parameter with 100% schema coverage, including the UUID pattern and the note that the id comes from search_grants. The description adds no meaning beyond the schema, so baseline 3 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?

States a specific verb and resource ('One public catalog grant in full') plus the fields returned, which implicitly contrasts with the bulk 'search_grants' sibling. It stops short of naming search_grants or search_funders explicitly, so differentiation requires inference.

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 'One public catalog grant in full' signals this is the detail-fetch counterpart to searching, and 'A grant that is not publicly listed is not found' supplies a when-not condition. No sibling is named as an alternative, so the routing guidance is clear but not explicit.

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?

Annotations already establish readOnlyHint=true and openWorldHint=false. The description adds meaningful behavioral context beyond that: data provenance from the latest Form 990-PF or Schedule I, ordering by largest givers first, 10 results per page, and the source_form "990" marker for Form 990 grantmakers.

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 front-loads the core action and scope, then adds relevant search dimensions and result behavior. It is somewhat dense but every sentence contributes useful information, with no major repetition or padding.

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?

For a read-only search tool with rich schema descriptions and annotations but no output schema, the description supplies enough context about data sources, ranking, pagination, and source marking. It could say more about returned fields or total result counts, but an agent can invoke it correctly from what is provided.

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%, so the schema already documents all four parameters thoroughly. The description reinforces the key filters by describing search by name, city, state, EIN, recipient state, and accepting-applications status, but it does not add syntax or constraints beyond what the schema provides.

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 names a specific verb and resource: search foundations, with a clear scope limited to those having a public GrantCue profile built from Form 990-PF or Schedule I data. It distinguishes this from searching grants by focusing entirely on foundation records and even notes how Form 990 grantmakers are included as marked source_form "990".

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 explains what can be searched and how results are ordered, giving implied usage context, but it never explicitly says when to use this tool versus siblings like get_funder or search_grants. There are no exclusions or alternative-routing instructions.

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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description focuses on what they cannot express: a hard page cap of 25, a reachable-result ceiling of 100, and the provenance caveat that grant text comes from funders. That last note usefully warns about data quality, though pagination/offset interaction is only partly covered.

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 short sentences, front-loaded with the resource and scope, then result-size limits, then the data-provenance caveat. No filler, though the 'same filters as the Discover page' framing assumes the agent knows that page.

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?

For a 12-optional-parameter, zero-required search tool with no output schema, the description covers scope, result caps and data provenance, and the schema fully carries parameter detail. The only gap is that the shape of a returned match record is never hinted at, which matters somewhat without an output schema.

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%, so all 12 parameters including sort defaults, enum meanings and offset limits are already documented. The description adds nothing parameter-specific beyond what the schema states, so the baseline 3 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?

States a specific verb and resource ('Search the public GrantCue grant catalog') and scopes it to federal, state, local and foundation opportunities. It is clearly a query tool distinct from get_grant/get_funder by name, but it never explicitly contrasts itself with those siblings.

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?

'with the same filters as the Discover page' implies the intended use case, and the 25-per-page / 100-result ceiling hints at when to narrow rather than page. However, it gives no explicit when-to-use-this-vs-siblings guidance (e.g., use get_grant for full opportunity detail, search_funders for organizations).

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