accept_coverage_divergences

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

With no annotations provided, the description carries the full burden of behavioral disclosure and excels. It reveals that accepting items modifies controls (adds/removes COs), creates a single version per affected control, validates each item independently, and supports partial batch success with an applied/skipped response. This level of detail far exceeds typical descriptions and gives the agent a clear mental model of side effects and edge cases.

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 well-structured: a clear lead sentence defines the action, followed by concise mechanics of behavior and a practical usage tip. Every sentence contributes new information—no filler, no repetition. The length is appropriate for the tool's complexity, and the key points are front-loaded.

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?

The description covers the purpose, usage workflow, parameter behavior, and operational nuances (validation, partial application, versioning). An output schema exists, so detailed return field documentation is unnecessary; the description still mentions the applied/skipped split, which is sufficient. For a batch mutation tool with no annotations, this is a complete and self-sufficient description.

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?

The schema already documents items, model_id, and change_reason (75% coverage). The description adds significant meaning by explaining how the 'kind' field in items dictates ADDs vs REMOVEs, and how the batch results in a version per affected control. It also provides a filtering strategy on p_covers, which enriches the semantics of the 'items' parameter beyond its structural schema definition.

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's function: accepting a set of coverage divergences as mapping changes in a batch. It explicitly explains that missing_mapping items ADD COs and spurious_mapping items REMOVE them, which distinguishes it from related tools like get_verdict_divergence (read) and dismiss_verdict_divergences (dismiss). The verb 'accept' and resource 'coverage divergences' are specific and unambiguous.

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 provides explicit workflow guidance: read rows first with get_verdict_divergence, optionally filter by p_covers, then pass items here. This clearly communicates when to use the tool relative to its reading counterpart. It does not explicitly enumerate exclusions (e.g., when to use dismiss_verdict_divergences instead), but the context is strong enough for an agent to select it appropriately.

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