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

With no annotations, the description carries the full load and does disclose meaningful traits: the operation is permissionless ('Anyone can send it'), the funds destination is constrained ('the prize goes to the poster only'), there is a timing precondition (10-minute grace), and the output is unsigned. It does not say what happens on an early/ineligible call or whether the prepared transaction can be reused, which are the remaining behavioral gaps.

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?

A single dense sentence with zero filler; the most important fact (prepares an unsigned refund) is front-loaded, followed by eligibility and then the fund-destination constraint.

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 two-parameter tool with no annotations and no output schema, the description covers preconditions, permissionlessness, and payout destination adequately. The main omission is that it never states what the prepared artifact looks like or that the caller must subsequently sign and submit it, which matters given there is no output 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% and both parameters are documented in the schema, including the provenance hint 'From get_bounties (includeClosed)' for bountyId, so baseline 3 applies. The description adds only indirect meaning for wallet — 'Anyone can send it' confirms the wallet is not the authorized sender — but gives no field-level syntax or format detail beyond the schema.

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 precise verb+resource: 'prepare (unsigned) the refund of an expired, unpaid bounty to its poster'. The qualifiers (expired, unpaid, 10-minute grace) make it immediately distinguishable from siblings like prepare_bounty_post, bounty_claim, and bounty_complete, and 'prepare (unsigned)' signals it produces an unsigned transaction rather than executing a transfer.

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 eligibility conditions are explicit (bounty must be expired and unpaid, and a 10-minute grace must have elapsed), and 'Anyone can send it' clarifies that no privileged caller is required. It stops short of naming an alternative tool or stating what to do when the bounty is not yet refundable, so it is strong context without full when/when-not routing.

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