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

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is complete. The description adds that it is limited to the caller's private runs and omits raw data, which is beyond the annotations and useful. However, it doesn't mention pagination behavior or the output size/limits beyond the schema's maximum limit, but that is minor. Overall, the description adds some value beyond annotations, but not a lot, so a solid 3.

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 is one sentence that front-loads the key facts: 'only the caller's private Accounting-run audit metadata' and 'newest first'. It then adds the omission note. Every word earns its place, no filler, and the critical scoping is immediately visible. Excellent.

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 tool is a simple list operation with common pagination parameters (limit, offset) and a status filter, plus annotations covering safety, the description is complete for basic invocation. It doesn't explain the exact format of the returned metadata or how filtering by status works, but the parameters are self-explanatory enough. The omission of raw data is clear, which satisfies a key contextual need. This is nearly complete, hence a 4.

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?

With 0% schema description coverage, all three parameters (limit, offset, status) are undocumented. The description does not mention these parameters at all, so it does not compensate. The parameter names are self-explanatory, and enums are in the schema, but without description coverage, the description leaves the agent to infer meaning from names. Given the low coverage, it could do more, but the parameters are simple and common, so a baseline 3 is fair.

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 clearly states the tool lists only the caller's private Accounting-run audit metadata, newest first, and explicitly omits raw source text and analysis results. This distinguishes it from siblings like get_accounting_run (likely fetches a single run) and create_accounting_run (creates runs), leaving no ambiguity about scope.

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 description clarifies the scope (private to caller) and order (newest first), but does not explicitly say when to use this over siblings like get_accounting_run or sync_accounting_tickets. The distinction is clear from scope and purpose, but there is no explicit guidance about alternatives or conditions that would favor this tool, so a 3 is appropriate.

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