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

Goes well beyond the annotations by disclosing the downstream side effect (one confirmation email to the owner with a Confirm button), the resulting followed-link change on the published listing, the missing_field failure mode, and the submission_id return value. The retry-with-idempotency_key instruction sits in tension with idempotentHint=false, but the schema explains the key only takes effect with an API key, so it is a limitation rather than a contradiction.

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 one-line purpose and minimum input, then layered with filling rules, email rules, and return/follow-up behavior. Sentences are dense but each carries a rule; the email sentence packs domain-matching, side effect, and link outcome into one long clause that could be split.

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 14-parameter, zero-required mutation with no output schema, the definition covers the input strategy, the side effect, the failure signal, and the return id. It omits what other errors can occur and any auth requirements for the idempotency key, but the schema supplies the former gap's context.

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%, so the baseline is 3; the description earns above that by adding cross-parameter logic the schema cannot express — that website alone suffices, that omitted fields are read from the site, and that unknown category values fall back to industry. It leaves the license_no dedupe rule to the schema and says nothing about address privacy here.

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 concrete verb and resource ("Submit a business") and immediately defines the minimum viable input: "The only thing you need is its website." It also names the follow-up sibling (get_submission_status) so the agent knows where this sits in the flow.

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?

Strong operational guidance: don't interrogate the owner unless missing_field is returned, category is optional, send email only when it is at the site domain or shown on the site, and reuse the idempotency_key on retries. It doesn't contrast against the sibling prefill_from_website, which also reads data from a site, so the agent has no routing rule between the two.

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