Subvencióname

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the bar is lowered. The description nonetheless adds a data-scope constraint not present in annotations ('solo empresas, no personas físicas'), which prevents wasted queries. It does not describe return format, but that is a minor gap against the annotated safety profile.

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 tight sentences: what it is, what it is for, and the hard scope limit. The resource definition is front-loaded and every sentence earns its place.

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 a fully documented schema and no output schema, the description is nearly complete. What remains missing is any hint of the result shape (e.g., contract fields returned), which an agent might want given there is no 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%, including the important subtlety that 'Con NIF se ignora el texto'. The description only restates the query axes and adds no syntax or precedence detail 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+resource in Spanish: 'Contratos públicos ya adjudicados' (already-awarded public contracts), with the search axes (NIF, texto, provincia). This clearly distinguishes it from siblings buscar_licitaciones and buscar_convocatorias, which cover pre-award stages.

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?

'Sirve para ver qué gana una empresa y cuándo vence cada contrato' gives a concrete use case, and 'Solo empresas: no hay datos de personas físicas' is an explicit scope exclusion. It does not name the sibling alternatives directly, so it stays below a 5.

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 cover read-only and closed-world status, but the description adds a critical behavioral trait: if the response includes 'ampliado' not null, the results come from a broader search and must not be presented as matching the filters. That fallback behavior is not available in annotations or schema and is highly useful for correct invocation and response handling.

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?

Purpose is front-loaded, followed by return fields, a filter tip, and the critical fallback warning. Every sentence earns its place: there is no output schema, so listing returned fields is valuable, and the 'ampliado' warning prevents misuse of broader results.

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 10 optional parameters, 100% schema coverage, and no output schema, the description supplies the missing return-field summary and the essential fallback interpretation. An agent has enough to call the tool correctly and report results appropriately.

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 10 parameters thoroughly. The description briefly reinforces the 'abiertas' filter but adds no new parameter syntax or edge-case semantics 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?

States a specific verb ('Busca') and resource ('subvenciones y ayudas públicas de España'), with sources named (BDNS y fuentes autonómicas). This clearly distinguishes it from sibling search tools for adjudicaciones and licitaciones.

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?

Provides operational guidance for using the 'abiertas' filter and for interpreting the 'ampliado' fallback, but never explicitly says when to choose this tool over siblings like ver_convocatoria or buscar_licitaciones. Usage is implied by the clear resource description but never spelled out as a selection rule.

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 safety profile is covered. The description adds real behavioral value beyond that: the data sources, the returned fields, and crucially the semantics of the 'ampliado' fallback (similar-but-not-matching results). It omits pagination/rate-limit behavior, but the fallback disclosure is genuinely useful 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?

Three dense sentences with zero filler: purpose and sources first, then return fields, then the critical fallback interpretation. Front-loaded and every sentence earns its place.

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 names the returned fields (objeto, órgano, importe sin IVA, fecha límite) and explains the 'ampliado' result shape, which is essential for correct agent behavior. Ten parameters are fully covered by the schema, but pagination defaults and ordering semantics beyond the enum are left implicit.

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 every parameter (q, cpv, tipo, provincia, importe ranges, etc.) is already documented with examples and constraints. The description adds no parameter-specific syntax or format detail beyond what the schema provides, 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 (buscar) and resource (contratos públicos de España) and narrows the scope to open-deadline tenders from three named sources (Plataforma de Contratación, TED, BOE). This lets an agent distinguish it from siblings like buscar_adjudicaciones (awarded contracts) without opening any schema.

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 'plazo de ofertas abierto' scoping and the explicit instruction on how to interpret a non-null 'ampliado' field give clear usage context and a fallback protocol. It does not explicitly name the sibling tools as alternatives, so it stops short of a full when/when-not routing guide.

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 safety profile is covered. The description adds genuine context by enumerating the payload (beneficiarios, importes, plazos, requisitos, enlace) and warning that the data should be checked before asserting a requirement or date – meaningful for a tool with no output 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?

Two tight sentences: content first, usage second, front-loaded and free of filler. Every clause earns its place.

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 field enumeration and the warning about verifying requirements/dates do useful work. Given the read-only annotations and single well-documented parameter, the definition is nearly complete; only minor details (e.g., what happens if the code is not found) are absent.

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 parameter is fully documented (pattern, example, source). The description only reinforces the meaning ('por su código BDNS') without adding syntax or format details 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 ('Ficha completa de una convocatoria') plus its key (BDNS code) and enumerates the returned content (beneficiarios, importes, plazos, requisitos, enlace). This clearly separates it from the buscar_* search siblings, which list rather than retrieve a full record.

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?

'Úsala después de buscar, antes de afirmar un requisito o una fecha' gives explicit sequencing and purpose, effectively pointing at the buscar_* tools as the prerequisite step. It stops short of naming a specific sibling or stating exclusions, so it is not a full 5.

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