find_errors

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

No annotations exist, so the description carries the full burden. It discloses the search scope (all run logs), specific error indicators, and return format (structured list with filename, line number, error type). It does not mention permissions or side effects, but as a read-only scan, this is acceptable.

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?

Three concise sentences front-load the main purpose, enumerate error types, and provide actionable follow-up. No redundant 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?

The description covers purpose, scope, error types, and return structure. It does not explain CESM context or output schema details, but an output schema exists and domain knowledge is assumed. Slightly more detail on the case_dir parameter would improve completeness.

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% since the description does not explicitly document the case_dir parameter. However, the context 'Scan all run logs in a CESM case' implies the directory, and the parameter name is self-explanatory. This partially compensates, but a direct statement would be stronger.

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 tool scans run logs in a CESM case for error indicators, listing specific error types. It distinguishes from sibling classify_error by positioning itself as the detection step.

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 explains when to use (to find errors) and suggests a follow-up action (call classify_error). However, it does not explicitly state when not to use or compare with siblings like check_cfl.

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