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

Annotations already declare destructiveHint=true, lowering the burden. The description adds context beyond that: it operates only on a LIVE incident, uses PATCH, and frames intents as status transitions. It still does not explain consequences of resolve/snooze or reversibility, but the added scoping is meaningful.

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?

Three tight sentences, front-loaded with the operation and ending with the endpoint. Slight redundancy in restating 'status transition' already present in the schema, but nothing wasteful.

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 4-parameter mutation with no output schema, the description covers purpose, scope (LIVE), the required-field constraint, and the endpoint. Return values needn't be explained without an output schema; only error or side-effect detail is missing.

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 100%, so baseline is 3. The description genuinely adds beyond the schema by stating the cross-field constraint 'at least one of changeSeverity or appendIntent is required', which is absent from the schema's required list (only incidentId), and clarifies the semantic of appendIntent.

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 (applies/updates via PATCH) and resource (an existing LIVE incident), plus the two mutating operations (changeSeverity, appendIntent). The 'existing LIVE incident' scoping and the PATCH endpoint make it clearly distinct from create_incident, get_incident, and list_incidents.

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?

The 'LIVE incident' qualifier and the named lifecycle actions (acknowledge/resolve/reopen/snooze) imply when the tool applies, and the 'at least one required' rule constrains invocation. However, there is no explicit statement of when to choose this over alternatives (e.g. create_incident) or any preconditions, so guidance is only implied.

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