Dúos

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false. The description adds useful behavioural context beyond them: it does not consume queries and does not expose other clients or global spend, which clarifies privacy and cost 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?

Three short sentences, front-loaded with the return payload followed by two negative-scope clarifications. Every sentence carries distinct value and nothing is redundant.

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?

An output schema exists and annotations are rich, so return values and safety profile need no elaboration. The description covers what is and isn't returned, leaving only minor gaps like pagination or freshness of the quota figures.

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?

Only one optional parameter and schema description coverage is 100%, so the enum for response_format is fully documented in the schema. The description adds nothing about the parameter, which is the expected baseline when the schema does the work.

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 plus the exact fields returned (plan, available queries, own AI budget) via 'Devuelve el plan, las consultas disponibles y el presupuesto propio de IA'. Scope exclusions ('no muestra otros clientes ni el gasto global') help separate it, but no sibling tool is named explicitly.

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 genera respuestas ni consume consultas' implicitly steers agents away from expecting generation, implying this is a read-only status check. However, no explicit when-to-use condition or alternative (e.g. duos_listar_consultas) is named.

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?

Goes well beyond the annotations by disclosing real consequences: the text is sent to external AI providers, it consumes ONE query from the plan and AI spend, and it returns jobId/status rather than the answer. The retry contract (reuse the same UUID for the same question, never change the message under that key) is behavioral detail the annotations cannot convey.

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?

Front-loaded with what the tool does, then cost, then prerequisite, then return/retry guidance in priority order. Dense but every sentence carries operational weight; only the dash-separated clauses make it slightly heavier than necessary.

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?

An output schema exists, yet the description still names the returned jobId/status and the tool that consumes it, plus cost and retry behavior. Nothing an agent needs to invoke this correctly — prerequisites, spend implications, next step — 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?

Schema coverage is already 83%, so most parameters are documented. The description still adds value by giving the idempotency_key its operational semantics — one fresh UUID per question, reuse only for retries of the identical message — which sharpens the schema's terser wording.

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?

Opening sentence gives a specific verb (crea) plus resource (consulta) and explains the actual mechanics: two independent initial analyses plus a cross-review by each model. It also routes to the sibling duos_obtener_resultado for the result, so an agent can distinguish this from list/quota tools without opening a 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?

Explicitly states the precondition (requires client intent), an explicit when-not (do not use as a free connection check), and the follow-up alternative (query jobId/status via duos_obtener_resultado). The retry rule for idempotency_key is also spelled out in operational terms.

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 readOnly/idempotent/non-destructive, and the description adds non-obvious context beyond them: an extra authorization requirement (duos:history) and the fact that it returns history only, not generated responses. It doesn't disclose ordering or retention behavior, but the additions are meaningful.

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?

Four short sentences, front-loaded with the core action, followed by the permission gate and the paging instruction. 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?

With an output schema present, the description needn't explain return values, and it correctly names nextOffset as the continuation signal. The auth prerequisite is stated. Its remaining gap is the undocumented limit/offset semantics, but overall it is sufficient to call the tool 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?

Schema description coverage is only 33%: limit and offset have no descriptions anywhere, and the description only indirectly gestures at offset via the nextOffset continuation hint. It adds no meaning for limit, offset bounds, or default paging size, leaving two of three params effectively undocumented.

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?

Specific verb+resource: 'Lista una página del historial propio de consultas' clearly states a paged listing of the caller's query history. It is distinguishable from siblings like duos_crear_consulta and duos_obtener_resultado, though it never names them explicitly to sharpen the boundary.

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 concrete operational guidance: needs the separate duos:history permission, does not produce answers (so use otra herramienta para generar/consultar respuestas), and says to keep paging with nextOffset while non-null. Lacks an explicit 'use X instead when…' routing to a sibling.

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 safety (readOnly, idempotent, non-destructive), yet the description adds genuinely non-obvious behavior: no model re-invocation, no quota consumption, honoring pollAfterMs between reads, and that an error does not constitute a finished result. Return shape is left to the 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?

Four short sentences, each carrying a distinct fact (scope, no side effects, polling rule, error semantics), with the scope constraint front-loaded. No filler, though the sentences are telegraphic and could flow slightly better.

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 an output schema handling return values and 100% schema coverage on the two parameters, the description fills the remaining gaps: quota/side-effect behavior, polling cadence, and error interpretation. Adequate for correct 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 100%, and the schema itself documents job_id (as returned by duos_crear_consulta) and the response_format enum. The description adds nothing beyond this, 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 ('Recupera únicamente un trabajo propio creado antes'), and the qualifier 'únicamente' plus 'trabajo propio' implicitly distinguishes it from duos_listar_consultas (listing) and duos_crear_consulta (creation). It never names a sibling explicitly, so differentiation is inferable rather than stated.

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 concrete usage context: only for jobs you created, respectful polling via pollAfterMs while pending, and the warning that an error is not a complete result. It stops short of explicitly steering to alternatives (e.g. what to call to create the job or list jobs).

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