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

Beyond the annotations it discloses the write side effect (email sent, record saved), the output boundary ('never returns order details'), and the verification semantics of the order number (marked unverified unless an identity token is supplied). What it omits is retry/failure behavior — the idempotency_key parameter implies safe retries while the description only says to call once, and no case confirmation/number is described.

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 action and its effect, then the routing clause, then constraints. The long enumerated scenario list is dense but each item earns its place by mapping to a reason value; the prose is somewhat run-on but has no filler sentences.

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 10-parameter open-world mutation with no output schema, the description supplies everything needed: side effects, no-return-value warning, identity-verification semantics, reply-channel requirement, and one-shot invocation guidance.

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 60% schema coverage, the description compensates by mapping business scenarios to reason values (including the special 'ai_automation' reason) and by explaining email/phone as the reply channel, the token's verification effect, and what the summary must contain. It leaves name, company, and product unaddressed, but those are self-explanatory strings already 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?

States a specific verb+resource ('Open a support case with the Vivid Ads team') and immediately discloses the side effects (emails the team, saves a record). It explicitly carves out its niche against the 26 siblings: 'for anything the other tools cannot do', then enumerates the concrete scenarios it owns.

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?

Gives positive triggers (damaged/faulty orders, address changes, proof help, samples, trade accounts, price match), explicit exclusions ('Never use this to take payment or approve a proof'), a cadence rule ('Call it ONCE per issue'), and preconditions ('after collecting a clear summary and the customer's email or phone'). It also routes sub-tasks to siblings: vivid_identity_verify for the token and vivid_upload_artwork for photos.

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