generate_runbook

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

No annotations are provided, so the description carries the full burden. It usefully discloses the structure of the generated artifact, which substitutes for a missing output schema, but says nothing about whether the result is persisted, whether generation is slow/LLM-backed, idempotency, or permissions required.

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 sentence that front-loads the action and resource, then lists the output sections in a natural order. No filler or redundancy.

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 a no-annotation, no-output-schema generator tool, the description covers the essential question of what the artifact contains, which is the main thing an agent needs. It falls short only on output format and the role of the optional service parameter.

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 the baseline is 3. The description reinforces the 'category' parameter ('for a specific error category') but does not explain how the optional 'service' parameter changes the generated runbook or what values are expected for either.

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 (Generate) and resource (incident runbook) scoped to a specific error category, and enumerates the sections the artifact will contain (triage, diagnosis, mitigation, resolution, postmortem). An agent can tell this apart from diagnose_issue or suggest_alert_rules, though no sibling is named explicitly.

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?

There is no when-to-use, when-not-to-use, or alternative guidance. The phrasing 'for a specific error category' hints at the input context but never says when an agent should reach for a runbook versus running diagnose_issue or cross_correlate on the same incident.

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