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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description usefully notes that results include the IVA rate, but says nothing about result ordering, relevance matching, or what happens when no code matches — relevant for a catalog search 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: what it does first, domain justification second. Minimal waste, though the invoice sentence is more motivation than actionable guidance.

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 two-parameter read-only search with no output schema, the description covers purpose, the returned fields, and domain context adequately. Missing only the shape of a result item (code, description, IVA) and empty-result behavior.

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 both parameters (descripcion, limite 1–50) are already documented. The description reinforces that descripcion is a product or service and that output carries the IVA rate, but adds no query-syntax or matching guidance beyond the schema examples.

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 (catálogo CABYS) plus the payload returned (códigos con tarifa de IVA). It does not explicitly differentiate from the sibling obtener_cabys, which by name appears to be the code-lookup counterpart, so sibling disambiguation is left implicit.

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 second sentence gives domain context — every good or service on a Costa Rican electronic invoice needs a CABYS code — which implies when the tool is needed. However, it never states when to prefer this over obtener_cabys or consultar_exoneracion, and no exclusions or prerequisites are given.

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=true, and the description is consistent with that, reinforcing that the source is the external Hacienda registry. It adds useful disclosure beyond the annotations by listing exactly which fields come back (régimen, estado, morosa/omisa, actividades económicas). It doesn't cover latency, rate limits, or what happens when the identification isn't found.

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, both load-bearing: the first defines the resource and its return payload, the second gives the usage context. No redundancy or filler.

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 a single required parameter, no output schema and lean annotations, the description carries the burden well by enumerating the returned fields and the accepted identifier types. Missing only edge-case behavior (invalid or not-found identification, response shape detail).

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 schema already explains the format with examples, so the baseline would be 3. The description adds genuine meaning by enumerating which identifier types are accepted (cédula física, jurídica, DIMEX, NITE), which the schema does not state.

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 (consultar) and a precise resource: the tax situation of a person or company in Hacienda, with an explicit enumeration of the data returned (nombre, régimen, estado, morosidad, actividades económicas). This is clearly distinct from the sibling tools (tipo_de_cambio, buscar_cabys, obtener_cabys, consultar_exoneracion), which operate on exchange rates, CABYS codes and exemptions.

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?

"Útil antes de emitir una factura electrónica" gives a concrete usage context, positioning it as a pre-invoicing verification step. However, it doesn't state when NOT to use it or point to alternatives (e.g., consultar_exoneracion for exemption status), so there are no explicit 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description usefully discloses that data comes from an external Hacienda registry and enumerates the returned fields. It says nothing about behavior when the authorization number is invalid or not found, which matters for an external lookup.

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 dense sentence that front-loads the resource and key, then lists the returned fields. No filler or redundant restatement of the schema.

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 one-parameter read-only lookup with annotations present and no output schema, the description covers source, key, and return fields, which is most of what an agent needs. The only gap is failure/not-found behavior.

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 already carries a format example ("AL-00020402-24"). The description restates that the input is the authorization number but adds no format, validation, or normalization 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?

Names the specific resource (exoneración de impuestos registered at Hacienda), the lookup key (número de autorización), and the fields returned (beneficiario, porcentaje, vigencia, CABYS). It is clearly distinguishable from siblings such as consultar_contribuyente or buscar_cabys. It stops short of a clean verb-led statement of operation, relying on the title for the 'consultar' action.

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 when to use it (when you have an authorization number and need exoneration details), and the 'a partir de su número de autorización' phrase anchors the input. It gives no explicit when-not-to-use guidance or pointers to alternatives like buscar_cabys when only CABYS coverage is needed.

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=true, so safety is covered. The description adds useful return-field information (description, IVA rate, categories) that matters because there is no output schema, but it omits invalid-code behavior and any rate/auth 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?

A single efficient sentence that front-loads the returned fields and ends with the key input constraint. No filler or repetition.

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 simple one-parameter lookup with readOnly annotations and no output schema, the description names the key return fields so the agent knows what to expect. Only explicit sibling routing and invalid-code behavior are 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?

With 100% schema coverage, the schema already documents the single codigo parameter with its 13-digit format and example. The description merely repeats the 13-digit constraint without adding format or validation meaning 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?

Names a specific resource (a 13-digit CABYS code) and states the fields returned: description, IVA rate, and categories. It does not explicitly distinguish itself from the sibling buscar_cabys, so it falls short of a 5.

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 13-digit exact-code phrasing implies this is a lookup tool for when the code is already known, but it never says so explicitly or names buscar_cabys as the alternative. Usage is implied rather than stated.

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=true, so the agent knows this is a safe external read. The description adds only the source (Hacienda) and the data composition, and says nothing about failure behavior when no rate has been published yet (weekends/holidays), timezone/date boundary of 'hoy', or caching/freshness of the fetch.

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 with the source and temporal scope front-loaded and the currency breakdown following. Every clause carries information; there is no boilerplate or 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?

With no output schema, the description correctly shoulders the burden of describing return content by listing the three rate pairs (USD buy/sell, EUR/CRC, EUR/USD). It stops short of stating the return shape or naming the currency codes, which leaves some ambiguity about how to parse the result, but the substantive coverage is solid for a no-argument lookup.

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 takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly makes no parameter claims and instead spends its words on output content.

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 resource ('Tipo de cambio de referencia de hoy') and its authoritative source ('según Hacienda'), then enumerates exactly which rates are included: USD buy/sell in colones and EUR in colones and dollars. An agent can tell immediately that this is a single-purpose FX lookup, and the sibling tools (taxpayer lookup, CABYS codes, exoneration) are clearly unrelated, so no differentiation is needed.

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 'de hoy' establishes the temporal scope and implicitly tells the agent this tool only answers today's reference rate, not historical series. There are no sibling alternatives to route between and no prerequisites to state, but the description never explicitly says 'use this when you need a current exchange rate for a calculation' or excludes anything.

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