decide_iteration_candidate

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

No annotations are provided, so the description carries the full burden. It hints at a gated workflow and a confirmation prerequisite, but says nothing about side effects, whether a decision is reversible, what state changes on accept vs reject, or whether a prior evaluation must exist. For a state-mutating decision tool this is a substantial gap.

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?

A single compact sentence with the action front-loaded and the prerequisite second; nothing is wasted. It is efficient, though the terseness contributes to the gaps flagged in other dimensions.

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?

An output schema exists, so return-value explanation is not required. But with 5 undocumented parameters, no annotations, and a vague notion of 'gated candidate', the agent lacks enough to call this correctly or know the workflow preconditions around the decision.

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% across 5 parameters. The description implicitly explains the verdict values (accept/reject/revise) and ties accept to user_confirmed, but session_path, candidate_id, and rationale are entirely undefined 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 verb 'decide' plus the three verdict actions (accept/reject/revise) make the operation legible, but the object is only described as a 'gated candidate', which is undefined. Nothing distinguishes it from the sibling evaluate_iteration_candidate, which an agent could easily mistake for the decision step itself.

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?

'accept needs user confirmation' is a genuine usage precondition that tells the agent not to accept unilaterally. However, there is no guidance on when to pick this over evaluate_iteration_candidate, record_iteration_feedback, or prepare_iteration_context, and no when-not conditions.

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