Search mail

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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds substantive behavior: full_text hits Thunderbird's global index over indexed headers/bodies while subject/author/body are per-folder substring matches, dates are ISO-8601, results are summaries only, and pagination continues via cursor=nextCursor. The closing caveat that requested folders are not proof of body/index coverage is exactly the kind of non-obvious limitation annotations cannot express.

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?

Six tight sentences, front-loaded with purpose and then the highest-value distinction (index vs per-folder matching). Every clause conveys operational information; nothing is repeated from 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 the description is not obligated to detail return values, yet it still flags that results are summaries and that the first page carries requestedScope and coverage. The remaining gap is parameter-level completeness for a 22-parameter tool with zero schema descriptions.

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% across 22 parameters, so the description must carry the load and it only partly does: it explains full_text versus subject/author/body and the ISO-8601 date format and cursor token. It leaves roughly a dozen parameters (min_size/max_size units, tag_mode interaction with tags, include_subfolders, account_id vs folder_id, to_me/from_me) with no semantic guidance at all.

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 resource ("Search the user's mail") and immediately clarifies the two search modes. It does not differentiate itself from sibling search tools such as search_global or search_conversation, so an agent cannot tell from this text alone which search entry point to pick.

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 useful in-tool guidance: combine full_text with filters, and route to mail_get when a body is needed. However, it never says when to use mail_search versus mail_list, search_global, or search_conversation, which is the primary ambiguity for an agent facing four search-adjacent siblings.

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