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

Goes well beyond destructiveHint=true by disclosing the irreversible business rule (only ONE refund per payment, partial refunds cannot be topped up) and the dry-run/confirm gating behavior. This is exactly the context an agent needs before moving money.

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?

The critical warning and confirm workflow are front-loaded, which is good. But the full reason-code glossary duplicates the schema's enum descriptions word-for-word, consuming a large share of the text for zero added information.

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, no-output-schema money-movement tool, it covers the safety essentials: preview behavior, irreversibility, and the partial-refund constraint. Minor gaps remain (transaction_id replay protection and error/duplicate-call behavior are only in the schema).

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 baseline is 3; the description earns more by explaining how confirm changes the call's effect and by tying refund_amount semantics to the one-refund-only constraint. It loses a point for restating the enum reason codes verbatim rather than adding meaning.

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?

Opens with an explicit verb+resource ('refund a payment, in full or in part') and a WRITE/moves-money label. The scope (one refund per payment) and endpoint are stated, which clearly separates it from read-only siblings like instamojo_get_refund and instamojo_list_refunds.

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 concrete usage protocol: call without confirm to get a preview, ask the user, then call again with confirm: true. It does not name sibling alternatives (e.g. use instamojo_get_refund to check status), so it falls just 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.