investigate_incident

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so safety is covered; the description adds concrete value by disclosing the composite output (RCA with abend reference and runbook link, RAG doc excerpts, full spool inventory, per-DD diagnostic excerpts). It does not warn that this is a heavyweight multi-source call, which is the main remaining gap.

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 front-loaded sentence that names the action, the scope and the bundle contents with zero filler. The parenthetical additions (abend reference, runbook link, RAG) are informative rather than repetitive.

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 carries the burden of describing the return surface and does so by enumerating every bundle section. Adequate for a 3-parameter read-only tool, though it omits any note about latency/cost of gathering all sources or the excerpt-size default.

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 jobId, environment and maxExcerptLines are fully documented in the schema. The description adds nothing parameter-specific (e.g. that omitting environment targets the server default, or that maxExcerptLines bounds each excerpt), 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?

Specific verb ('Assemble') plus resource ('full incident bundle for a job') with an enumerated inventory of what the bundle contains (status, RCA, RAG excerpts, spool inventory, DD excerpts). It reads as an aggregator, but the description never contrasts it with the overlapping siblings analyze_job_failure and analyze_root_cause, so an agent must infer the boundary.

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 only implied by the word 'full' and 'Assemble' – the description suggests a deep, one-shot investigation, yet it gives no explicit when-to-use/when-not and names no alternatives among the many diagnostics siblings. Minimum viable routing guidance.

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