resumir_paper

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

No annotations are provided, so the description carries the full burden — and it delivers. It discloses that the summary comes from the abstract (not full text), that it is generated by the local LLM, that results are cached (same paper never summarized twice), and precisely how failures behave: null summary, origin 'indisponivel', and a warning explaining the reason instead of fabricating content. This is exemplary edge-case disclosure.

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?

Compact and well-structured: purpose sentence first, then behavioral constraints, then the single argument. Every sentence earns its place — the caching, fallback, and source details are all high-value. No filler or repetition 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?

Complete for a single-parameter tool. An output schema exists, so return values need not be spelled out in the description. The description covers purpose, input provenance, caching, and failure modes. The only minor gap is that it doesn't explicitly enumerate the output schema fields, but that is the output schema's job.

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 0%, so the description must compensate — and it does. It explains paper_id as the key returned by buscar_papers_novos (usually the DOI), giving both the provenance and format of the value. For a single-parameter tool this is sufficient; a slight gap is not spelling out the expected DOI format explicitly, but the source reference covers it.

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: a structured summary (problema, método, achado, relevância) of a paper. It clearly distinguishes from the sibling buscar_papers_novos (search vs. summarize), and even references that tool as the source of the input key, so an agent cannot confuse the two.

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 context is implied rather than stated. The Args section references 'a chave devolvida por buscar_papers_novos', which implies the correct workflow (call search first, then summarize). However, it never explicitly says 'use this after buscar_papers_novos' or gives a when-not-to-use condition beyond the abstract/LLM fallback, so the guidance is implicit.

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