approve_referral

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

The description discloses the non-obvious two-call preview/confirmToken protocol, which is real behavioral context the annotations do not carry, and 'Write:' correctly matches readOnlyHint=false and destructiveHint=true. It does not say what approval actually changes or whether it is reversible, which is a meaningful gap for a destructive-flagged operation.

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?

Two sentences, front-loaded with the action, no filler. Every clause (scope, write classification, confirm flow) carries information an agent needs.

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 destructive, three-parameter mutation with no output schema, the definition covers the essential call protocol and safety posture. Only the consequences of approval (what state changes, reversibility) are 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 67% and the schema already documents confirm and confirmToken; the description adds the sequencing semantics that the schema alone leaves implicit (first call returns token, second call supplies confirm:true plus that token). referralId remains undocumented in both places.

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 ('Approve a referral') plus the qualifying scope ('held for review'), which distinguishes it from void_referral, pause_referral, resume_referral and approve_due_commissions. An agent can route correctly without opening any 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?

The 'held for review' clause gives a clear precondition for when this tool applies, and the second sentence prescribes the exact invocation sequence. It does not name an alternative tool or state exclusions (e.g., what to do if the referral is not held), so it stops short of full when/when-not guidance.

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