search_mail_headers

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the useful behavioral note that 'message bodies are not fetched', which informs the agent that results will lack body content. However, it doesn't describe the output shape, pagination, or header fields returned beyond the schema.

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 short sentences, zero filler. The critical operational facts (date format, bodies not fetched) are communicated efficiently with no wasted words.

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?

The tool has a rich output schema and heavy annotation coverage, which raises the baseline. Given 9 parameters including a dual-limit pattern (limit vs scan_limit) and multiple overlapping filters (query, folder, subject, from_filter, unseen), the description could benefit from explaining how these interact. It is adequate but leaves the dual-limit semantics ambiguous.

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 0% with 9 parameters, so the description must compensate for parameter understanding. It adds the date format convention (YYYY-MM-DD) and clarifies that bodies aren't returned, which helps interpret query/filter params. However, it doesn't explain the semantics of scan_limit vs limit, or the interplay of query/folder/subject/from_filter, leaving room for more detail.

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 verb 'search' plus resource 'mail headers' clearly establishes the tool filters mail by headers (as opposed to body content). The date format note (YYYY-MM-DD) adds practical specificity. However, it doesn't explicitly distinguish from read_mail or list operations among siblings, though the 'headers only' scope differentiates it well.

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 implies this searches headers rather than bodies, which gives some context, but it doesn't explicitly state when to use this vs read_mail, mail_status, or list_folders. No when-not or alternative tool guidance is provided. The context is minimally clear but underdeveloped.

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