sapiens_repertorio

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

Annotations only convey readOnlyHint=false and openWorldHint=true, so the description carries the burden — and it delivers. It discloses that any logged-in user mutates only their own collection, that the server re-resolves providers and canonicalizes title/cover/year, that upsert/dedup is keyed on (userId, source, externalId), and that tool entries count as 'used' simply by being added. No contradiction with 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?

The description is long, but the complexity of 10 actions and 16 parameters justifies it. It is organized into readable sections (reads, mutations, one-shot capture, AI tools) and front-loaded with the core purpose. Some prose is dense and run-on, but nearly every sentence carries necessary operational information.

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 large multi-action tool with no output schema, this is unusually complete: it covers action semantics, parameter provenance, failure modes, dedup behavior, authentication requirements, and disambiguation rules. Omitted details such as exact return shapes for list/search are secondary because the action flows are fully specified and the schema defines the inputs.

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 schema description coverage at only 56%, the description compensates heavily. It explains the most error-prone parameters: source/externalId must come from a resolve candidate and must never be fabricated, status inference from natural language (assisti/zerei/li=completed, quero=backlog, etc.), and toolId must come from search_tools. It also clarifies provider meanings such as manual=OMDb for film/series and twitch for games.

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 exactly what the tool is: a personal collection (acervo) spanning media types and AI tools, and enumerates all action families. It clearly distinguishes the two sub-domains (media providers vs the aitag tool catalog) and maps actions to resources, making the scope unambiguous even among many sibling tools.

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 explicit when-to-use protocols for every action family: reads vs mutations, the resolve-then-add_item flow, one-shot capture trigger phrases, and the failure rule that the agent must not add an entry if resolve returns empty or providerKeyMissing. It also gives concrete when-not-to-act guidance and says to ask only when candidates are ambiguous.

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