gmail_get_message

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds value beyond the annotations by disclosing exactly what the read returns and, crucially, what it does NOT return ('sem conteudo' — attachment content is excluded). The 'corpo em texto' disclosure (text body only) also sets expectations about format. 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?

A single Portuguese sentence packs the retrieval key, the return structure, and an explicit exclusion with zero wasted words. Every phrase earns its place: 'pelo id', 'cabecalhos, corpo em texto', 'lista de anexos (nome/tamanho, sem conteudo)'.

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 read-only tool with safety covered by annotations, the description is largely complete: it defines inputs (id), outputs (headers, body, attachment metadata), and an exclusion. The main gaps are the unexplained max_chars truncation behavior and the meaning of profile, which an agent would need to correctly size or filter requests. No output schema exists, so the return-scope description carries the full burden and mostly succeeds.

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 effectively 0% — the schema provides only bare titles ('Profile', 'Max Chars', 'Message Id') with no descriptions. The description clarifies message_id's role ('pelo id') but says nothing about max_chars (presumably a body truncation limit, default 20000) or profile (which account context to use). With zero schema descriptions, the description must compensate and only covers one of three parameters.

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 states a specific verb and resource ('Lê uma mensagem pelo id' — reads a message by id) and goes further to enumerate the exact return scope: headers, text body, and attachment list with name/size. It naturally distinguishes itself from siblings like gmail_search (finding messages) and gmail_list_labels (listing labels) by clarifying this is an id-based retrieval returning message content.

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 usage context is implied rather than stated: the phrase 'pelo id' signals the agent must already possess a message_id, implying gmail_search is the precursor. However, there is no explicit when-to-use guidance, no mention of alternatives, and no statement of when not to use this tool (e.g., if attachment content is needed).

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