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

Annotations already declare idempotentHint=true and destructiveHint=false, and the description reinforces this by specifying the retry semantics ('Identical retries keep the same revision') and adding an optimistic-concurrency requirement (expectedRevision from a previous read). It also scopes which field is customer-facing, context the annotations do not provide, though conflict/failure behavior is not described.

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 with no filler, and the approval precondition is front-loaded ahead of the mechanical constraints. Density is high, though the telegraphic phrasing of the middle sentences costs a little readability.

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?

An output schema exists, so return values need no explanation, and the approval gate plus revision semantics are covered. However, for a six-parameter write tool the description omits the meaning of status (APPROVED vs RETIRED), the significance of boardId, and any conflict or failure behavior, leaving meaningful gaps.

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 0% across 6 parameters, so the description carries the explanatory burden. It clarifies 'wording' (the only customer-facing text) and the role of 'expectedRevision', but leaves name, summary, status, and boardId entirely unexplained, covering only a third of the parameters.

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 pair and resource ('Store or revise an incident state') plus a key scope qualifier ('the user has explicitly approved'), which separates it from sibling save_approved_statement and save_approved_cause by object type. It stops short of naming those siblings, so differentiation relies on the resource noun alone.

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?

It gives a clear precondition for use ('a state the user has explicitly approved') and a condition for the mutation path ('A changed state requires expectedRevision from a previous read'), which tells the agent when a read must precede the call. No explicit alternative tools or when-not-to-use cases are named.

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