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

With no annotations, the description carries the full burden and does disclose meaningful behavior: Ronin never moves money, signing is hosted, and the key is used for this call only and never stored. It stops short of covering failure modes, idempotency, or whether proof is mandatory for certain rails.

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 dense sentences, front-loaded with the action and its most important constraint (no money movement). Every clause earns its place, though the parenthetical alternative slightly interrupts the flow.

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 mutation tool with no annotations and no output schema, the description covers the safety-critical concerns (money is not moved, key is ephemeral) that an agent most needs. Gaps around return values and error behavior are minor given the tool's narrow scope.

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% (task and proof partly documented, proof fully described). The description's key-handling note largely repeats the schema's own description of 'secret', and it never explains what 'task' is (the 64-hex identifier) or when 'proof' is expected, so it adds only marginal meaning 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 specific verb+resource ('Record that you paid for a task') and immediately bounds it with 'Ronin never moves money', so an agent understands this is an attestation, not a payment execution. It also names the sibling alternative ronin_submit for self-signing, distinguishing it from the rest of the ronin_* set.

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 clear precondition ('after paying on the agreed rail') and names the alternative path ('or sign yourself with ronin_submit'). It does not state explicit when-not conditions (e.g. don't call before payment settles), but the sequencing guidance is strong.

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