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

Annotations already declare non-read-only, non-idempotent, open-world behavior, so the bar is lower; the description adds meaning by saying it returns an UNSIGNED transaction and is "Non-custodial" — i.e. no key material is needed and no funds move at this step. That is useful context beyond the annotations, though it omits failure conditions (e.g. calling before the deadline) and what the payload looks like.

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 terse fragments with no wasted sentences, but the lead is an HTTP route rather than a statement of what the tool does, so the most decision-relevant information is not front-loaded. Jargon (flop-htlc, hasStation.refundEscrow) consumes space without aiding selection.

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 non-idempotent, open-world transaction-building tool with no output schema and 33% parameter coverage, the description leaves material gaps: the role of "from", the meaning of "hasStation.refundEscrow" as the return, what happens if invoked before the deadline, and the follow-up signing/submission step. It is not adequate for an agent to call this correctly on first try.

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 only 33%: only "to" (refund destination SS58) is documented. The path placeholder :id maps loosely to jobId, but the description never explains it, and the "from" parameter has no explanation in either the schema or the description. With low coverage the description should compensate, and it does not.

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?

The description indicates an endpoint (POST /jobs/:id/refund) and an output (an unsigned hasStation.refundEscrow transaction), so the purpose is inferable, but it is stated as a route and contract jargon ("flop-htlc") rather than a clear verb+resource sentence. It does not differentiate itself from crew_build_unsigned, crew_job_payout, or crew_submit_signed.

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?

"after the deadline" supplies a genuine precondition for calling this tool, which is more than nothing. However, it offers no exclusions, no alternative path (e.g. when to use the generic crew_build_unsigned or to submit via crew_submit_signed), and no statement of what to do with the unsigned result.

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