Conqueia (¿Con qué IA?)

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds the return fields (título, resumen, URL) and the relevance ordering, which is useful behavioral context, but omits pagination and does not disclose that the query is bounded to a closed directory beyond the annotation.

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 compact sentences, with purpose front-loaded before the return-value note. Mild redundancy from brand naming, but no wasted phrasing.

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 states what each result contains (title, summary, URL) and how results are ranked, which is enough for a 4-parameter search tool. It stops short of noting result limits or 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%, with every parameter documented in the schema (slug examples for tema, enum for tipo, limit bounds, and query examples). The description adds nothing parameter-specific, 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 (Busca) and resource (el directorio) plus the content types it covers (casos, skills, apps, herramientas, guías) and the language. An agent can tell this is the search tool, though it never explicitly contrasts itself with siblings like recomendar or ver_ficha.

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 when-to-use guidance and no mention of alternatives. With siblings such as recomendar, temas, and ver_ficha available, the description gives no help deciding which to call, leaving the agent to infer that 'search' is the generic query entry point.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered externally. The description adds genuinely useful behavioral context – the fixed 30-day recency window, Spanish-language explanations, and that each item carries a URL – but says nothing about result volume, freshness sequencing, or pagination.

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 subject and recency window front-loaded, followed by the content types and the output format. No filler, no restatement of the title, nothing to trim.

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 zero-parameter, read-only lookup with no output schema and full annotation coverage, the description covers what the agent needs: what it returns, in what language, over what time window, and that URLs are included. Only the absence of any routing hint against the four sibling tools keeps it short of complete.

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 no parameters, so there is nothing for the description to disambiguate; the baseline for a zero-parameter tool is 4. The description correctly signals a parameterless, fetch-everything call rather than implying hidden filters.

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 concrete resource and scope: AI news from the last 30 days, broken into models, features and tools, returned in Spanish with source URLs. It is clear what an agent gets back. It does not, however, differentiate this from siblings like 'temas' or 'ver_ficha', so the agent cannot tell from the text alone which one to pick.

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?

Usage is implied rather than stated: the 30-day window and 'lo nuevo' framing make it obvious this is the tool for recent AI developments. There is no explicit when-to-use vs when-not guidance and no mention of the sibling tools (buscar, recomendar, temas, ver_ficha), leaving routing to inference.

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 it as a safe, read-only, idempotent, non-open-world operation, so the safety profile is covered. The description adds genuinely useful behavioral detail beyond that: the result set is capped at 5 items and each recommendation includes an explanation ('por qué encajan'), which tells the agent what to expect without an 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?

A single sentence that front-loads the input and then the output with rationale. Slightly comma-heavy and could be tightened, but every clause carries information (input type, example, result count, result contents).

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 recommender with annotations covering safety, the description supplies the inputs, the count of results, and what each result contains, which is enough to invoke it correctly. Remaining gaps (language handling, whether results vary over time) are minor.

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 there is only one parameter, so the baseline is 3. The description adds value by showing a concrete natural-language example ('quiero contestar reseñas de Google más rápido'), clarifying that the input is free-form user phrasing rather than keywords or filters.

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 concrete verb pair (recibe/devuelve) and a concrete resource: 5 fichas, casos reales y herramientas ranked by fit. This clearly separates it from siblings like ver_ficha (single card) or buscar (search), though it never names an alternative 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?

Usage is implied by 'recibe la tarea del usuario' and the quoted example, so an agent can infer it is for open-ended 'how do I do X' requests. There is no explicit statement of when to prefer this over buscar or temas, and no exclusion criteria.

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 closed-world behavior, so the safety profile is covered. The description goes beyond them by disclosing the shape of the result — per-topic ficha counts plus slug and URL — which matters because there is no output schema. It stops short of saying whether the topic list is fixed/exhaustive or how large it typically is.

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 resource named first and the returned fields appended. No preamble, no redundancy, nothing that could be cut.

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 zero-parameter, read-only listing tool, the description plus annotations cover everything needed to call it correctly: what it lists, and what each entry contains. With no output schema present, spelling out the returned fields (count, slug, URL) closes the only real gap.

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 the baseline of 4 applies. The description correctly implies a no-argument call by presenting the result set as a complete enumeration of directory topics.

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 ("Lista") and resource ("los temas del directorio") and illustrates the resource with concrete examples (ventas, atención al cliente, facturas). It also enumerates what each item carries (ficha count, slug, URL). It does not explicitly contrast itself with siblings like buscar or ver_ficha, but the purpose is unmistakable.

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?

Usage is only implied: an agent can infer you call this to discover topic slugs/URLs before drilling into fichas or searching. There is no explicit when-to-use statement and no mention of alternatives such as buscar or ver_ficha, so routing must be inferred from the sibling names.

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, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: the return format is markdown, the content is a FULL card (implying a shorter preview may exist elsewhere), and the fields returned vary by ficha type.

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, front-loaded with the return value and followed by the input form. The middle list of card contents is slightly long but each item is informative and cheap, 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?

With no output schema, the description carries the burden of describing the return value and does so adequately for a read tool with zero required parameters. It omits error/pagination behavior, which is a minor gap given the low complexity.

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%: the URL example, the slug definition, and the enum plus its 'novedad' note are all documented in the schema. The description only restates the URL-or-tipo+slug combination, adding no syntax or constraint beyond what the schema already 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 concrete verb and resource ('Devuelve una ficha entera') and enumerates the payload an agent will get back (pasos, prompt, precios, pros y contras, fuentes). It is clearly distinguishable from a search or news-listing tool, though it never names or contrasts the siblings (buscar, novedades, temas).

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 gives the two invocation paths (URL, or tipo+slug) which implies the identifier must already be known, but it never says when to call this versus 'buscar' or how to obtain the slug/URL in the first place. 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.