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

Goes well beyond the annotations by disclosing real side effects: editing can email subscribers and post to Slack. Combined with annotations (destructiveHint=true, idempotentHint=true) and the guard against inventing statuses, an agent understands both the blast radius and the safety constraint before calling.

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?

Four short sentences, zero filler, and the most important constraint (side effects / only when asked) is front-loaded ahead of the update_id nuance and the status warning.

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?

It covers the destructive/notification profile and one parameter, which matters for a 9-param mutation with no output schema. But it never explains how omitted/null fields behave, what body versus update_body targets, or how component_ids are applied, leaving real ambiguity before a destructive call.

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 coverage is 0% across 9 parameters, so the description carries the full burden, yet it only explains update_id (edit a posted update instead of the incident) and gestures at status. body vs update_body, title, impact, component_ids, and slug vs public_id are all left undocumented.

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+resource ("Edit an incident") plus a useful disambiguation: with update_id it edits a posted update rather than the incident. That distinguishes the two behaviors without naming the sibling post_incident_update directly, so an agent still has to infer which tool posts versus edits.

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?

"Run only when the user asked" is an explicit precondition, and "Never invent a status the user did not ask for" constrains behavior. There is no explicit routing vs. post_incident_update for creating a new update, which is the main nearby alternative, so it falls short of full when/when-not guidance.

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