search_emails_metadata

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

With no annotations provided, the description carries full behavioral burden and excels: it discloses that the search is server-side against body text, that only metadata envelopes are returned (never body excerpts), and that the JSON shape varies (envelope vs bare array) based on server-reported match counts. This is rich, accurate, and goes beyond minimal requirements.

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?

The description is moderately sized but every sentence serves a purpose: establishing the sibling relationship, clarifying the metadata-only output, providing a use case, and explaining the conditional envelope format. It is front-loaded with the most important distinction and avoids fluff, though it could be tighter by removing redundant phrases like 'never preview or body excerpts' after already saying 'only metadata'.

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 tool with no output schema and no annotations, the description is remarkably complete: it covers purpose, relationship to sibling search_emails, when to use it, what it returns, and the dynamic JSON envelope. It does not mention pagination behavior or potential errors, but for a straightforward search/metadata tool, the provided context is sufficient for a typical agent to select and invoke 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?

The input schema covers all three parameters (query, limit, ascending) with basic descriptions, giving 100% schema coverage. The tool description adds meaningful behavioral context for the query parameter (it searches body text on the server side), but it doesn't provide additional per-parameter semantics beyond what the schema already offers. This meets the baseline for high schema coverage.

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 'Same as search_emails (free-text search across subject and body) but returns ONLY metadata on each match', clearly specifying the action, resource, and scope while distinguishing it from its sibling search_emails. It also enumerates the exact fields returned, leaving no ambiguity about what the tool does.

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 description explicitly states when to use the tool: 'Use when a content match is required … but the matches must not surface body fragments to the caller.' It also references search_emails as the alternative for full-text results. However, it does not explicitly contrast with other metadata-related siblings like advanced_search_metadata, so it stops short of comprehensive alternative guidance.

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