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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely useful traits beyond that: results are metadata only (not bodies), ordered best-match-first, and mailbox-wide by default unless folderId narrows it — none of which is in 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?

Front-loaded with purpose, then scope, then routing, then syntax and concrete examples — four tight sentences with no filler. Every clause (including the quoting note and examples) earns its place by preventing malformed queries.

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?

With no output schema, the description compensates by stating the return shape (metadata, not bodies) and ordering, and annotations cover the safety profile. The only mild gap is not enumerating which metadata fields come back, which is minor for a search tool.

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 coverage is 100%, making 3 the baseline, but the description goes further by documenting the query grammar (from:, to:, subject:, received>=YYYY-MM-DD, hasattachments:yes, OR, quoted phrases) that the schema does not express. It also reinforces folderId's scoping behavior, adding real meaning over the parameter list.

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 a mailbox") and immediately scopes the output ("message metadata — not bodies") and the default scope (whole mailbox unless folderId is given). This cleanly separates it from get_outlook_message (reads one message) and list_messages, so an agent can pick it 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?

Explicitly routes: "Use this to find messages, then get_outlook_message to read one, or move_messages to file them," naming both the trigger and the follow-on tools. It lacks an explicit when-not clause (e.g., versus list_messages or search_gmail_messages), so it falls just short of a full 5.

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