jev_compare_attempts

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

The description discloses that the tool is 'cheap' (cost/performance signal), returns 'stuck/progress signals and an advisory control signal,' and explicitly does not choose the next fix. This goes beyond the schema and annotations (which are absent). It doesn't mention side effects or failure modes, but for a read-only comparison tool, the disclosed behavior is reasonably complete.

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 three sentences, each with a distinct purpose: what it does, when to use it, and what it returns/doesn't return. It is front-loaded with the core action and scoped efficiently. No wasted words.

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 description is complete for a comparison tool: it states the trigger condition, the output type, and the limitation. The output schema exists, so return values are partially documented. The main gap is that the Attempt object's fields are not semantically explained, but the schema provides their names and types, and the description's 'stuck/progress signals' gives a high-level sense of the output.

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%, so the description carries the burden of explaining parameters. The description names the key inputs ('two unsuccessful implementation attempts') and the output signals, but it does not explain the individual fields within the Attempt object (failure, approach, hypothesis, diff_summary, changed_files) or the client metadata. The schema provides field names and types, but the description adds no semantic detail about how these fields are used in the comparison.

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 states a specific verb ('compare'), a specific resource ('two unsuccessful implementation attempts'), and a clear scope ('cheap comparison'). It also distinguishes itself from siblings by noting it 'does not choose the next fix,' which helps an agent understand its role relative to other jev_* tools.

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 when to use it: 'Use when repeated work may be spending frontier inference on the same failed strategy.' This gives a clear trigger condition. It also states what it does not do ('does not choose the next fix'), which helps an agent avoid over-trusting the tool's output.

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