Resolve Verdict Divergences

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

With no annotations, the description carries the full burden and does so: it declares the tool is mutating, describes per-item validation producing applied vs skipped (stale, would orphan, already so), states that reason is recorded on each control's history, and explains that a dismissal is keyed to the row's current verdict input so it reappears once the control or objective changes. These are exactly the side-effect and persistence semantics an agent needs.

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 core verb and mutating nature are front-loaded in the first sentence, and the action-specific blocks are clearly delimited. It is dense but every sentence carries operational information; only the formatting density slightly taxes readability.

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 5-parameter mutating tool with an output schema (so return shape needn't be described), the description covers both actions, their validation outcomes, and the persistence behavior of dismissals. Nothing an agent needs to call it correctly is missing.

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 80% (baseline 3), but the description adds real meaning: it explains what each kind value does to the model ('missing_mapping ADDS its CO', 'spurious_mapping REMOVES it') and clarifies reason length thresholds per action. It doesn't document server_version, keeping it just short of a 5.

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 pair and resource ('Accept a batch of coverage divergences as mapping changes, or dismiss a batch of divergences. Mutating.'), and explicitly names the sibling get_verdict_divergence as the source of the rows to act on. An agent can distinguish this mutating resolve tool from the read-side get_verdict_divergence without opening either 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?

Gives explicit when-to-use for each action: accept means 'the structural model was right and the LLM was not' changes; dismiss means the divergence should be suppressed. It even routes the agent to filter rows by p_covers in get_verdict_divergence before accepting, which is concrete pre-invocation guidance.

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