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

Annotations only declare the generic profile (not read-only, open-world, non-idempotent, non-destructive); the description adds the substantive mechanics: a 6-digit emailed verification code, a post-verification review consisting of an automated website/product check plus a human when needed, and a 'you are live' notification with the link. It also discloses binding input policy not captured elsewhere at workflow level (own-domain website required, free webmail rejected).

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 audience and action, then workflow, then policy, then outcome — a logical order with no filler. It is dense and long for a single tool, but each sentence carries either a routing rule or a constraint; only the closing Reevi profile-management detail is marginally beyond what an agent needs to call it.

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 9-parameter, non-idempotent, open-world submission tool with no output schema, the description covers the full lifecycle: pre-check, submission, code delivery and reading, verification call, human review, and final notification. An agent can execute the whole flow without additional 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 schema already documents all nine fields and the baseline is 3. The description still adds meaning beyond it: the requirement that the website be the company's own and the explicit rejection of free webmail domains (gmail, qq.com, 163.com, outlook) is a substantive constraint on the `email` parameter that the schema only implies.

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 (submits a request to be added to Reevol Source) and immediately scopes the audience (suppliers not yet listed). It is clearly distinguishable from search_suppliers (check first) and verify_supplier_listing (the next step) which it names explicitly.

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 explicit preconditions and alternatives: 'search_suppliers first to make sure the company is not already listed', then after the request the agent must read the 6-digit code from the inbox and call verify_supplier_listing. The routing between this tool and its two siblings is unambiguous.

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