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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds non-obvious behavior: results are ordered newest-first, which fields are matched, and that the output is thread ids rather than message content. This is meaningful context beyond the annotations.

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 tight sentences, front-loaded with the action and scope, then the return value and the follow-up tools. No sentence is padding.

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?

There is no output schema, so the description correctly compensates by stating the return type (thread ids) and the ordering. Safety is covered by annotations and params by the schema. Missing only edge-case behavior such as empty results or multi-mailbox merge behavior, which keeps it at 4.

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 80%, so the schema already documents limit, query, state, participant and unread_only. The description restates the query/participant matching targets but adds no syntax, format, or interaction details (e.g., how query and participant combine). Baseline 3 is correct.

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 (Search) plus resource and scope (connected mailboxes' threads, newest first) and enumerates the searchable fields (subject, sender, body, participant address). An agent can distinguish it from siblings like read_email_thread or find_communications without opening a schema.

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?

Clearly frames the workflow context: it returns thread ids to be consumed by read_email_thread, and replies go through draft_email + reply_to_thread_id. It stops short of naming when NOT to use it or contrasting it with other search siblings (find_communications, search_freeform), so 4 rather than 5.

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