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

The annotations establish that this is a mutating, idempotent, non-destructive operation, but the description adds substantial behavioral detail beyond them: unknown usage stays pending, settled credits can increase only from confirmed existing receipts, interrupted attempts must reuse the idempotency key, and failed partial jobs remain failed even if billing settles.

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 description opens with the core purpose, then layers in constraints and edge cases in descending priority. Every sentence carries information, and there is no filler or repetition of the schema or annotations.

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?

Given the output schema exists, the description need not explain return values. For this billing-reconciliation operation, it covers when to use it, what it will not do, how retries work, and how partial failures are treated, which is complete enough for correct invocation.

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 supply parameter meaning. It does so for both parameters: jobId must identify a terminal job the caller created in this workspace and runtime, and idempotencyKey must be kept the same for an interrupted attempt.

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 states a specific verb and resource: reconcile billing for a terminal research job. It also scopes the job as one the caller created in this workspace and runtime, which clearly separates it from enrichment_start or enrichment_get.

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 gives an explicit precondition: use only when billingStatus is reconciliation_pending. It also states several when-not conditions (never starts, resumes, repeats research, purchases credits, or accepts caller-supplied costs). However, it does not name an alternative tool to use when the precondition is not met.

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