check_refund_policy

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

Annotations already declare readOnly, idempotent, non-destructive, so safety is covered. The description adds value beyond them by disclosing the decision outcomes (auto_approve | needs_human_review | reject) and that reasons are returned, which tells the agent this is a triage-style gate rather than a boolean check.

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 purpose sentence, then a compact Args block and a one-line Returns. No filler, and each line conveys information not present in the bare schema.

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?

An output schema exists, so the description need only frame inputs and scope, which it does fully for all four parameters including the optional one's default behavior. Nothing an agent needs to invoke this 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 description coverage is 0%, so the description carries the full burden and does: it gives a concrete order_id format (ORD-1004), explains amount is in major units with an example (24.99), states reason is the customer's motivation, and specifies as_of as YYYY-MM-DD defaulting to today.

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 ('Check whether a refund is allowed') plus an explicit scope boundary: 'Does NOT issue the refund.' An agent can immediately tell this is a policy-evaluation tool, not a mutation.

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 negation 'Does NOT issue the refund' implies the workflow position (evaluate before acting) and the 'who must approve it' framing signals it is a decision gate. It does not name an alternative sibling tool or state explicit exclusions, so it falls short of a 5.

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