dismiss_verdict_divergences

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses a critical behavioral trait: 'A dismissal is keyed to the divergence's current verdict input hash, so it auto-clears (the row reappears) once the underlying control or objective changes.' It also explicitly states the tool does NOT change the model. The description lacks some details like reversibility or permissions, but the disclosed auto-clearing behavior is significant and beyond the schema/name.

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 concise, front-loaded with the primary action, and every sentence earns its place: purpose, usage condition, key behavioral caveat, and supported row types. There is no irrelevant content or redundancy, and the line break separates the main action from the usage details effectively.

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 tool's purpose, when to use it, its key behavioral side effect, and the types of divergences it handles. Since an output schema exists, the description need not explain return values. It lacks explicit mention of prerequisites (e.g., how to access reviewed rows) and direct referral to alternatives like accept_coverage_divergences, but for a tool with this complexity, the provided context is sufficient.

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 75%, so the schema already documents most parameters. The description adds that the tool 'Works for coverage AND group_sufficiency rows', which clarifies the 'items' parameter's accepted kinds and reinforces the schema's requirement that control_id is needed for coverage kinds and group_id for group_sufficiency. However, this is marginal beyond the schema, and server_version remains undocumented in both schema and description.

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 action: 'Dismiss a set of divergences' and clarifies that it does so 'WITHOUT changing the model'. It specifies the scope ('Works for coverage AND group_sufficiency rows') and distinguishes from sibling tools by emphasizing the structural model was right while the LLM was not, which differentiates it from accept_coverage_divergences or other divergence-related tools.

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 guidance on when to use the tool: 'Use for rows you have reviewed and judged not valid.' It also clarifies applicability to both coverage and group_sufficiency rows. However, it does not explicitly mention when not to use it or offer direct alternatives to other divergence tools like accept_coverage_divergences, though the contrast is implied by 'Dismiss' vs 'Accept'.

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