codex_diagnose

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

With no annotations, the description carries the full burden. 'Read-only' discloses the safety profile, and the guidance on inputs adds context, but it omits cost/tier behavior, caching (noCache), timeouts, or what the response looks like — all left entirely to the schema.

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 short sentences, front-loaded with the purpose, then the trigger, then the required inputs and safety note. 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?

For an 11-parameter tool with full schema coverage and no output schema, the description adequately covers purpose, trigger, and inputs. It leaves return-format and cost behavior to the schema, which is acceptable, though a note on the read-only/no-write guarantee relative to siblings would round it out.

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 100%, so all 11 parameters are already documented in structured data. The description's mention of 'symptom, the error output and the few files involved' loosely maps to objective/paths but adds no syntax or detail beyond the schema, so baseline 3 applies.

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 goal (find the root cause of a bug or failing test), which an agent can act on. However, it does not distinguish itself from plausible siblings like gemini_analyze, quick_check, or codex_review, so an agent must infer which analysis tool applies.

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?

'Call it as soon as your first hypothesis fails' gives a concrete trigger condition for when to invoke it, and it specifies what to supply (symptom, error output, files). It stops short of naming alternatives or conditions to prefer a sibling instead.

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