Search authorized Gmail accounts for meeting minutes by semester, returning numbered candidates so the professor can choose which ones to record as backup.
BACKUP para hosts SEM integração de e-mail: busca atas no Gmail das contas autorizadas
na CLI (expeditto gmail-login). Devolve candidatas numeradas; o docente escolhe quais registrar.
| Name | Required | Description | Default |
|---|---|---|---|
| semestre | Yes |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only and open-world. The description adds real behavioral context beyond them: authentication happens via the CLI ('expeditto gmail-login'), and the return is a numbered candidate list rather than a direct write. This is genuinely useful for an agent.
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 dense sentences, zero waste, with the scoping constraint and the auth prerequisite front-loaded before the return behavior. Nothing extraneous.
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's note that it returns numbered candidates is necessary and helpful. However it leaves the one parameter undocumented and gives no hint about result volume, filtering, or failure modes if no authorized account exists.
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?
One required parameter ('semestre') with 0% schema description coverage, and the description never mentions it or its expected format. With no schema help and no description compensation, the agent gets no semantic guidance for the sole input.
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 ('busca atas no Gmail') and scopes it as a BACKUP path for hosts without email integration. It doesn't name the sibling (registrar_atas_gmail) explicitly, but the routing condition makes the distinction inferable.
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 states when to use it (backup for hosts WITHOUT email integration) and what follows (the professor selects which candidates to register). No explicit exclusions against named alternatives, but the triggering context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.