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

Annotations only say it is a non-idempotent, non-destructive, closed-world write with no read-only hint. The description adds crucial behavior annotations miss: nothing is granted synchronously, a human owner must see the request in Approvals and e-mail and sign it, and the result arrives asynchronously. This is exactly the extra context an agent needs.

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 dense sentences, front-loaded with what the tool does, then what happens and when to use it. Slightly packed but no sentence is wasted; the human-approval caveat is well placed.

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 mutating request tool with no output schema and thin annotations, the description covers outcome (approval e-mail/Approvals queue), timing (async, retry later), and follow-up tooling. Nothing an agent needs to invoke it correctly 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 coverage is 100% and the schema itself documents each field richly (currency ISO code, seller 'match' semantics, caps). The description summarizes the same fields but adds no syntax or format detail beyond the schema, so the 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 (ask) plus resource (spend budget/mandate) and scopes it to THIS agent, clearly separating it from siblings like my_budget (existing budgets) and budget_request_status (tracking). An agent can identify the tool's role without opening the 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?

Gives explicit trigger conditions ('after a refusal that names a currency you have no budget in ... MANDATE_NOT_FOUND with currency=…') and names the follow-up path ('retry the purchase later, or check budget_request_status'), routing the agent to the correct sibling.

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