delete_message

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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds substantial context: two-phase approval with preview, audit logging, request expiry, deduplication, rate limits, the exact execution behavior (moved to Deleted Items / expunged), and that GigaMail never empties the trash. This goes far beyond the structured hints and gives an agent full visibility into side effects.

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?

Every sentence earns its place. The key constraint (two-phase, human-approved) is front-loaded immediately after the one-line purpose. Subsequent sentences cover expiry, deduplication, rate limiting, audit log, preview content, execution semantics, trash behavior, return value, and the alternative tool — all without fluff. It is dense but efficient.

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 destructive tool with no output schema, the description fully covers what the agent needs: the approval flow, all possible statuses, parameter semantics, return value, and post-execution effects. It even clarifies edge cases like deduplication and rate limiting. There are no missing pieces an agent would need to call it 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 coverage is 100%, so the baseline is 3, but the description enriches each parameter: it explains the message_id format per account type, the account_id default behavior, and the request_id two-phase lifecycle (omit → approval_required, then pass to execute). This adds meaning beyond the schema's own descriptions, so a 4 is warranted.

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 opens with 'Delete one message.' — a specific verb and resource — and immediately distinguishes itself from move_message by recommending it for reversible tidying. This clearly separates the tool from siblings like delete_folder and move_message, so an agent can pick it correctly without ambiguity.

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 the tool (permanent deletion) and when to prefer the alternative ('For reversible tidying prefer move_message'). It also outlines the mandatory two-phase human-approval flow, telling the agent exactly what the first and second calls do and that the agent cannot approve. No inference needed.

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