compare_evidence

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

With no annotations, the description carries the full behavioral burden and discloses almost nothing: it does not state whether comparison is costly, requires spans from the same run, or how discrepancies are represented. The output schema covers return values, but no operational context is offered.

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 efficient sentence with the purpose front-loaded and no filler. It is appropriately sized, though slight under-specification rather than tightness is the limiting factor.

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?

An output schema exists so return values need not be described, and the tool is structurally simple with two required params. Still, the meaning of run_id and the relationship between run and spans go unexplained, and with no annotations the definition leaves real gaps for an agent to infer.

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 must compensate and it does not. 'Multiple evidence spans' hints that span_ids takes a list, but run_id is entirely unexplained (why is a run needed to compare spans?), leaving both required parameters semantically opaque.

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 gives a specific verb ('Compare') and resource ('evidence spans') plus a scope qualifier ('multiple... side by side') and a goal ('evaluate agreement or discrepancies'). It does not, however, distinguish this from siblings like verify_claims or find_counterevidence, which occupy overlapping semantic territory.

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 guidance on when to use this tool versus verify_claims, find_counterevidence, or get_evidence. The 'evaluate agreement or discrepancies' phrasing implies a comparison scenario but names no condition or alternative.

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