analyze_job_failure

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful output shape ("rich 3-section report") and discloses that it extracts step/program/fix, but says nothing about behavior on edge cases — a job that succeeded, an unknown jobId, or spool-unavailable conditions — nor about cost or latency of the multi-step analysis.

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?

Two short sentences, front-loaded with the action and immediately followed by the concrete outputs. "Rich" is slightly promotional filler, but the rest of the text is dense and earns its place.

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?

With no output schema, the description usefully compensates by naming the report contents and its three-section structure, which tells the agent what to expect back. What's missing is routing context within a large sibling set and any statement of prerequisites (e.g., needing a failed jobId first).

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%, with jobId, spoolDd, environment, and includeEvidence all documented in-schema, so baseline is 3. The description adds no parameter-level meaning, such as when to override spoolDd or how environment resolution interacts with list_environments.

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?

States a specific verb and resource ("Analyze a failed job") and enumerates the concrete artifacts produced (abend code, failing/cancelled step, program, suggested fix). It does not differentiate itself from closely related siblings such as find_failed_jobs, summarize_abends, lookup_abend_code, or analyze_root_cause, so an agent must infer which one fits.

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?

Usage is implied by "a failed job" — the agent can infer this is the deep-dive after a failure is identified — but there is no explicit when-to-use framing, no pointer to find_failed_jobs as the discovery step, and no exclusions against summarize_abends or analyze_root_cause.

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