BearQ: Refine Test Cases

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

The description describes a mutation operation ('refines', 'improves their steps'), but the annotation readOnlyHint=true contradicts this. No additional behavioral context is provided beyond the contradictory annotation, leading to confusion.

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 short and front-loaded, with two sentences conveying purpose and usage. The parameter list is redundant but not overly verbose. It achieves conciseness without missing key information.

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 annotation contradiction and lack of return value description, the description is incomplete. The tool mutates data but is marked read-only, which misinforms the agent. Without output schema, return behavior is unmentioned.

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?

The parameter 'testCaseIds' is described in both the description and schema identically, with 100% schema coverage. The description adds no new meaning beyond what the schema already provides, so baseline score of 3 is appropriate.

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 'refines', the resource 'BearQ draft test cases', and the outcome 'improves their steps for promotion to regression tests'. It distinguishes from siblings by specifying 'specific' test cases via IDs, unlike refine_all or refine_by_area.

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 explicitly says 'Use when a draft is incomplete or has drifted from its intent.' This provides clear context. While it does not mention when not to use or list alternatives directly, the specificity implies exclusion of other refine tools.

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