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

Beyond the readOnly/idempotent annotations, the description discloses the auth scope required, the refusal semantics for unverified or foreign domains (ownership never disclosed), that ai_assessment.summary is untrusted third-party content to be treated as data not instructions, and that filing is never performed through the tool. That is a rich behavioral profile an agent could not derive from annotations or schema.

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 trigger and the one-domain scoping constraint, and every sentence contributes (auth scope, result shape, untrusted-content caveat, no-filing rule). It is dense and somewhat long, but no sentence is filler; only the return-field inventory is arguably redundant given the output schema.

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?

For a read-only, six-parameter tool with an output schema and full annotation coverage, the description supplies everything an agent needs: invocation trigger, auth prerequisite, scoping limits, ordering default, row-level drill-down, refusal behavior, and the prompt-injection caution. Return values are understood not to need explanation, and the description still sketches them without bloating.

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 the enum values, limits, and filters are already fully documented. The description adds only marginal parameter context — the default threat-first ordering and that row_id pulls an evidence packet plus filing targets — which largely restates the schema descriptions. Baseline 3 applies when the schema carries the semantics.

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?

The description states a specific verb and resource — returns the account's watched lookalikes for ONE verified domain — plus the ranking (highest threat % first) and the optional row-level evidence packet. The scope is unmistakable, though it never names the sibling check_lookalikes, so an agent must infer the scan-vs-watched distinction from context.

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?

It opens with an explicit trigger ('Use this when a signed-in operator asks which lookalike domains ... the watch has found, how risky they are, or for one's takedown evidence') and states the prerequisite token scope (monitoring:read). It also routes row-level requests to the row_id parameter, but offers no explicit when-not guidance versus check_lookalikes.

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