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

Annotations already declare the safe-read profile, and the description adds substantially on top: auth requirement, the untrusted-data warning about message text, result ordering ('newest first'), the highlight encoding (** with ~80 chars of context), and three concrete failure modes (400 missing_query, 400 invalid_date, 404 inbox_not_found).

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?

Front-loaded with the when-to-use clause, then read-only/auth, inputs, return shape, and errors in a tight sequence with no filler. Some parameter text duplicates the schema verbatim, which is the only redundancy.

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, and the description compensates by spelling out the return object shape (including extracted_text and highlights), ordering, and error surface. An agent has everything needed to invoke and interpret this call.

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 100%, so every parameter is already documented. The description largely restates those semantics (q matching rules, limit default/max, exclusive ISO-8601 bounds) and mainly adds value by tying before/after and q to their error codes, so the baseline of 3 is appropriate.

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 ('find mail inside one inbox') plus the searchable facets (keyword, sender, recipient, subject). The 'inside one inbox' scoping cleanly separates it from the account-wide cooper_search and from cooper_search_threads.

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?

Opens with an explicit trigger ('Use this when you need to find mail inside one inbox ... and you want the matching words highlighted'), which tells the agent the exact situation this tool fits. It stops short of naming alternatives such as cooper_search or cooper_search_threads for cross-inbox or thread-level search, so the exclusions are implicit.

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