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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, but the description adds genuinely new behavior: it never raises a protocol error and instead returns an {"error": ...} object, and it is always safe to retry after fixing input. The "FREE" cost signal is also useful. It repeats the read-only/idempotent claims from annotations, which keeps it out of the top band.

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-loads the purpose, then scope, then example I/O, then exclusions and error contract – each block is one tight sentence or fragment. The inline return example is arguably redundant with the output schema, but it is compact and earns its space as a call-shape illustration.

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 free, two-parameter read-only validator, everything an agent needs is present: what it checks, what input looks like, what comes back, the error contract and retry safety, and which siblings to use instead. Nothing material is missing.

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 two parameters are already documented, including that subject may be empty. The sample input object restates that relationship but adds no syntax, limits, or edge-case meaning beyond the schema. Baseline 3 applies.

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 (audit outreach copy) plus the exact risk classes it checks (spam triggers, deliverability). It names the two siblings it is not, so an agent can route correctly 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?

"Use on the body of an outreach message" gives the positive case, and the next sentence gives two explicit exclusions with the sibling that covers each: subject_line_scorer for subject lines, sequence_planner for send schedules.

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