Namli

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 adds useful behavior beyond that: it returns available ('libres') names first, establishing output ordering, and frames itself as a secondary fallback. It does not cover rate limits or the availability-checking mechanism, so not 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?

Two sentences, both front-loaded and earning their place: the first establishes what the tool does and its output ordering, the second routes the agent to the better alternative. Zero 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?

No output schema, so the description must carry the return-value story, and it does state that free names come first. It falls just short of complete because the pais parameter (likely scoping the availability check to a country) is neither explained nor referenced.

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 50%: descripcion and semillas are already documented in the schema and the description merely restates them ('descripción', 'palabras semilla opcionales') without adding syntax or format detail. The other two parameters (pais, cuantos) are untouched, so the description only partially compensates for the coverage gap – baseline 3.

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 (propone/devuelve) and resource (nombres para un proyecto) and names the sibling verificar_nombres as the preferred route, so an agent can distinguish this tool from its siblings 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?

Explicitly says when to use it ('Es un respaldo') and when not to ('si puedes, genera tus propias ideas y revísalas con verificar_nombres, que da mejores nombres'). The alternative tool and the condition that selects it are both 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?

Annotations only declare readOnlyHint/openWorldHint; the description adds real behavioral context: the 10–40 second latency from querying official registries, the sources consulted, the returned verdict with evidence/links/dates, and the caveat "No es un concepto jurídico." This goes well beyond the annotations.

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 the core action, then sources, return format, and usage directive. Dense and nearly waste-free, though the long single-paragraph run-on of source lists is slightly heavier than needed.

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 fully compensates: it explains the return shape (libre/parecido/ocupado with evidence, links, dates), the sources, the latency, and the legal limitation. An agent has everything needed to call it and act on the result.

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%, so all three parameters are already documented, including the reasoning that descripcion determines which collisions matter. The description adds only marginal framing (country-specific domain variants tied to país) rather than new syntax or format guidance, 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 (revisa/verifica) and resource (nombre de proyecto, marca, app o empresa) with the exact sources it checks (SIC Colombia, EUIPO, domains, web, GitHub, npm) and the verdict format. Extremely concrete. It does not distinguish itself from the near-identical sibling verificar_nombres (plural), so it falls short of the sibling-differentiation bar for 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?

Gives a strong explicit directive ("ÚSALA SIEMPRE antes de recomendar un nombre") plus the branch action when the verdict is "ocupado" (propose another and re-verify). However, it never names the alternative tools (sugerir_nombres / verificar_nombres) or when to prefer them, so the routing guidance is incomplete.

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 adds genuinely useful behavior: what the quick check covers (dominios, web, npm) and that trademarks are excluded ('sin marcas registradas'), which explains why a cheaper pass is acceptable here.

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, zero filler, and the key qualifiers ('RÁPIDA', the 10-item cap, the sibling hand-off) are front-loaded. Everything stated 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?

Adequate for a read-only batch check: purpose, scope, limit, and the escalation path to verificar_nombre are all present, and no output schema exists so return values need no explanation. Minor gap: the undocumented 'pais' parameter is left unexplained and the result shape of the quick pass is not hinted at.

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 67% ('nombres' and 'descripcion' documented, 'pais' not). The description repeats the 10-item cap already encoded as maxItems but adds no syntax, format, or country meaning, so it neither compensates for the coverage gap nor misleads.

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 ('Revisión RÁPIDA de varios nombres a la vez') with explicit scope: domains, web and npm, up to 10 per call. It distinguishes itself from sibling verificar_nombre by labeling this the quick pass versus the 'revisión completa'.

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 an explicit when-to-use ('filtrar una lista de ideas que tú mismo generaste') and names the follow-up alternative ('luego pasa el o los mejores por verificar_nombre para la revisión completa'). The routing between the two verification siblings is unambiguous.

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