resumir_conduta

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It clearly states that the response always includes a literal citation, states whether the citation was actually found, includes the PDF link, and explains what happens when prerequisites are missing (returns only the link and a warning). This is unusually transparent about failure modes and return contents.

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 front-loaded with a clear purpose sentence, then adds differentiation, return behavior, prerequisites, and parameter documentation. It is longer than a two-sentence ideal, but every sentence carries useful information and none is redundant. Minor extra length is justified by the tool's non-trivial behavior.

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?

The description covers the tool's purpose, the exact inputs, the return characteristics, the prerequisites, and the fallback behavior. Since an output schema exists, return-value details are not required here. There is no missing information an agent would need to invoke 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 0%, and the schema provides only titles. The description compensates fully by explaining both parameters: pcdt_id is the identifier returned by consultar_protocolo and may also be a condition name without the revision note (e.g., 'asma'), and contexto_clinico is the concrete clinical situation. This adds essential meaning beyond the bare schema.

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 starts with a specific verb and resource: 'Resume a conduta de um PCDT para um contexto clínico específico.' It differentiates itself from the sibling tool by saying it does not return the whole protocol but extracts only the part relevant to the clinical context. This makes the tool easy to distinguish from consultar_protocolo.

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 states the intended context ('para um contexto clínico específico') and contrasts with returning the full protocol ('Em vez de devolver o protocolo inteiro'), which implies when the sibling would be used. It also gives preconditions (local LLM and collected full protocol text) and the fallback behavior. However, it does not explicitly instruct to use consultar_protocolo when the full protocol is needed.

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