rca_analysis_compare

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description does not need to repeat these. It adds value by specifying the return format ('JSON comparison with consensus_causes and model_disagreements'), which provides insight into behavior beyond annotations. No contradiction.

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 for purpose, followed by clear Args and Returns annotations. No unnecessary words, and the most critical information is front-loaded. Every sentence earns its place.

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 existence of output schema, the description appropriately says 'Returns: str: JSON comparison...'. It covers the main input constraint (2-10 result_ids) and purpose. However, it omits details on authentication (token) and optional client_id, and does not mention error handling or edge cases. Still, enough for a straightforward comparison tool.

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 0%, meaning the description does not explain individual parameters. The description mentions 'list of 2–10 result_ids' but does not clarify 'token' or 'client_id'. With 3 parameters fully defined in schema but only partially described, the description fails to add sufficient meaning beyond the schema.

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 verb 'compare' and the resource 'multiple RCA results', and specifies outputs like 'overlapping root causes' and 'model disagreements'. This distinguishes it from siblings like rca_analysis_get_result (single result) and rca_report_compare (report comparison).

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 implies usage after RCAs have been run, but does not explicitly state when to use this tool versus alternatives. It could have mentioned prerequisites (e.g., 'use this after generating multiple RCA results with rca_analysis_run') or exclusions (e.g., 'not for comparing reports'). The input requirement of 2-10 result_ids is clear but no further guidance.

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