evaluate_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 behavioral burden. It does add one useful trait — the operation does not promote the candidate — but it never says whether evaluation is persisted, whether it mutates session state, what happens to prior feedback, or what prerequisites (e.g. an active run must exist) are required.

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 short sentence with the key constraint ("without promoting it") front-loaded and no wasted words. Its brevity is achieved through under-specification rather than disciplined compression, so it is efficient but not adequate.

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 presence of an output schema relieves the description of explaining return values, but for a 4-required-parameter workflow tool with zero annotation and zero schema-description coverage, the description is far too thin. It omits the meaning of gating, the workflow position relative to decide_iteration_candidate, and any prerequisite or side-effect information.

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 five parameters, and the description provides no meaning for session_path, candidate_run_dir, addressed_feedback_ids, change_summary, or changed_artifacts. An agent must guess the expected format of paths, whether run dirs are relative, and how feedback IDs are sourced.

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?

"Gate a new run against the active run without promoting it" names the verb (gate/evaluate) and the resource (a candidate run vs. the active run), which is more specific than the tool name alone. However, "gate" is domain jargon and the description never explains what gating produces (a verdict? a score? recorded evidence?), and it does not explicitly distinguish itself from sibling decide_iteration_candidate.

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?

There is no statement of when to call this versus decide_iteration_candidate, record_iteration_feedback, prepare_iteration_context, or inspect_iteration, all of which sit in the same iteration workflow. The only implied guidance is the parenthetical "without promoting it," which hints at a pre-decision step but leaves the ordering of the workflow to inference.

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