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

Goes well past the readOnly/idempotent annotations: it discloses result ordering (most recent first), deduplication semantics (same person once per address), scope limits (only contacts your addresses exchanged mail with), and what a no-match actually means. It also explains the meaning of returned fields (notes, blocked, snoozed_until) and the has_more/next_cursor handoff.

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 example mapping, then builds outward to scope, identity, and pagination — good ordering with no filler. Some sentences are long and chain multiple clauses (the identity/dedup sentence in particular), which slightly reduces scanability.

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 naming the notable returned fields and the pagination contract. Combined with the no-match semantics and contact-scope caveat, an agent has what it needs to call this correctly; only `limit` behavior (default page size) is unstated.

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?

With 0% schema description coverage, the description carries the burden and mostly does: search (partial name or address/domain), identity_id (narrows which address's copy of a contact), and cursor (driven by has_more). Only `limit` is left unaddressed, which is a minor gap given its 1-200 bounds are in the schema.

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?

Opens with a concrete verb+resource framing ("Turns a name into an address") and an example mapping ("email Priya" → search: "priya"). This makes it unmistakably a contact lookup tool, distinct from siblings like update_contact, verify_sender, or search_messages.

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?

Usage is clear from the title and first sentence (find a recipient to write to), and the description handles the key decision points: partial name vs. domain search, per-identity filtering, and pagination. It does not name alternatives such as update_contact or verify_sender, so it stops short of explicit when-not guidance.

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