Search emails

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context that annotations cannot convey: the returned FTS coverage signal and the need to check it before concluding an email is absent, plus the case-insensitive substring matching semantics of sender filters.

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, each carrying distinct information: what is searched, how to interpret empty results, and one matching-semantics detail. No filler or repetition of the tool name.

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 return values need not be explained. For an 11-parameter filter tool with full schema documentation, the description supplies the one thing the schema cannot (the FTS coverage caveat). It is complete enough, though it could note the account/mailbox scoping interaction.

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. The description goes beyond the schema by specifying that sender filters are case-insensitive substring matches, which the from_addr/to_addr schema text ('name, address, or address fragment to match') does not state explicitly.

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 and dual resource scope: 'Search local envelope data and indexed body content.' Clear what it does, but it draws no boundary against siblings like list_recent, get_email, or get_thread, so the agent must infer when this broad search is preferable.

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 FTS-coverage caveat gives useful guidance on interpreting results ('check coverage before treating no matches as proof'), which is implied usage guidance. However, there is no explicit when-to-use versus list_recent or get_email, and no statement of prerequisites or exclusions.

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