actiond_diagnose

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

The description details behavioral specifics beyond the annotations, such as handling jobs without error output by reporting 'no_error_output' instead of silently dropping them. It also aligns with the readOnlyHint and idempotentHint by describing an analytical, non-mutating operation.

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 dense and informative, but slightly redundant in phrasing (e.g., restating that omitting job_id analyzes recent failures). Still, each sentence contributes useful detail and the structure flows logically from purpose to parameters to output.

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 compensates for the absence of an output schema by enumerating what the agent can expect: root-cause category, error code, severity, confidence, evidence lines, likely files to change, and an aggregate summary. It also explains the edge-case behavior for jobs without error 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?

Both parameters are fully described in the schema, and the description adds practical semantics: job_id selects a specific job, while omitting it analyzes recent failures, and limit caps the number analyzed with a default of 5. This goes beyond the schema's basic definitions.

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's specific purpose: diagnosing failed CI/CD jobs and generating actionable fix suggestions from logs. It also explicitly distinguishes itself from related sibling tools by directing users to actiond_log for raw logs and actiond_action_get for job metadata.

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 provides explicit guidance on when to use this tool ('Reach for this first whenever a job fails') and when to use alternatives (actiond_log for raw logs, actiond_action_get for job metadata). This gives clear decision-making context for an agent.

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