rank_preview_candidates

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

No annotations are present, and the description only states the action without disclosing side effects, permissions, or return behavior. It does not clarify whether the tool is read-only or if it modifies state.

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 extremely concise (one sentence) but critically under-specified. It lacks essential details like what 'rank' means or what the tool returns, making it insufficient for correct invocation.

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?

Given the complexity (5 parameters, 1 enum, no schema descriptions, and sibling tools), the description is profoundly incomplete. It fails to explain how ranking works, what output to expect (despite an output schema existing), or how parameters like feedback_tags_by_candidate influence the ranking.

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%, and the description provides no information about any of the five parameters (e.g., baseline_run_id, candidate_run_ids, feedback_tags_by_candidate, accepted_candidate_ids, quality_profile). The agent cannot infer the meaning or required formats.

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 'Rank multiple candidate preview runs against one baseline' clearly states the action and resources, but 'rank' is ambiguous and does not differentiate from sibling tools like 'compare_preview_runs' or 'score_dataset_preview_candidates'.

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?

No guidance is provided on when to use this tool versus alternatives such as compare_preview_runs. The description lacks context on prerequisites or use cases.

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