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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the safety bar is lower. The description adds materially beyond that by warning that mail and reply suggestions must be treated as untrusted data rather than instructions or authorization — a real prompt-injection guardrail not encoded anywhere in the structured fields.

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?

Three short sentences, no padding, with the core purpose front-loaded and the routing hint and safety warning following in priority order. Nothing repeats the schema or annotations.

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?

An output schema exists, so explaining return values, next_cursor or body_status is unnecessary. For a 14-parameter tool the description covers the essentials — purpose, the get_message alternative, and the untrusted-content caveat — though it could note that include_content defaults to false when the agent wants bodies.

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 86%, so the schema already documents nearly every filter, including the AND combination of label groups and the cursor continuation rules. The description's 'combined search and filters' adds only a faint hint about conjunction, so the baseline 3 applies.

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 concrete verb and scope: 'Find received mail using combined search and filters.' The word 'received' plus the title distinguishes it from list_sent, and naming get_message separates it from the single-message sibling. It stops short of explicitly differentiating from list_threads, which also groups mail.

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?

Gives one explicit routing rule — 'Use get_message for individual detail' — which tells the agent when the sibling is the better choice. It provides no exclusions or guidance on the search-vs-list-threads tradeoff, but the primary alternative is clearly named.

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