budget_reconcile

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

Annotations only establish the safety profile (not read-only, closed-world, non-destructive); the description adds genuinely useful behavioral context: the required worker-quiescence precondition, the dispatchStopped attestation, and the explicit non-effect (does not authorize a new generation). It stops short of saying what actually happens to the held reservation (released vs. written off) or whether the call is idempotent.

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 hard precondition is front-loaded and every sentence carries information: precondition, procedure, effect, and scope limit. It is dense but not padded; a small amount of restructuring would improve scannability.

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 output schema and only minimal annotations, the definition is adequate on preconditions but leaves key gaps: what the settlement does to the reservation, what the response contains, and behavior on a failed attestation. An agent can sequence the call but cannot predict its effect.

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 must carry all parameter meaning. It explicitly covers dispatchStopped:true and implicitly maps reviewer/approvalText to 'Record the researcher approval', but says nothing about actualUsd (is it the verified billed amount, a delta, or a replacement?), projectId, or operationId. Partial compensation only.

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 name plus description convey a specific verb+resource: reconcile/settle a budget reservation stranded by a hard process exit, only after billing is verified. 'Settle an uncertain operation' is somewhat abstract on its own, but the stranded-reservation framing and the contrast with sibling project_budget make the intent readable without opening the schema.

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?

It states a hard precondition ('ONLY after the researcher verifies actual provider billing'), a sequencing requirement (stop every server/worker that could still dispatch it, then attest dispatchStopped:true), and a scope limit ('Does not authorize another generation request'). This is explicit when-to-use and when-not guidance with the ordering spelled out.

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