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

Goes well beyond the annotations: it discloses the credit cost, that an email is sent to a third party, and that the operation is asynchronous with the report only available after the applicant acts. These are the facts an agent needs to avoid burning credits or misreading an empty immediate response; the annotations only supply the generic non-read-only, non-idempotent profile.

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?

Three tight sentences: capability, then precondition, then follow-up path. Cost and side effect are front-loaded before the procedural instruction, and nothing is repeated from the schema or annotations.

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?

With no output schema, the description correctly tells the agent not to expect the result synchronously and where to retrieve it. For a non-idempotent tool that spends a credit it could say more about duplicate-call risk and failure modes, but the core invocation picture is complete.

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 50% – applicant_name and applicant_email carry no schema descriptions, and the description compensates by instructing the agent to confirm those two values with the user, implying they drive who receives the email. The two documented optional parameters (purpose, requested_by_name) need no further explanation.

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 chain: consumes one credit to create a bank-based income check, emails the applicant a Plaid link. The mechanism (Plaid bank connection) and channel (email) are specific enough to separate it from report-reading siblings like get_report.

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 a clear precondition ('confirm the applicant's name and email with the user before calling') and routes the agent to the follow-up tools (list_verifications, get_report) once the applicant connects. It does not, however, explain when to choose this over the similarly named sibling start_income_verification, which is the most likely confusion point.

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