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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is covered; the description still adds real substance by disclosing cascade scope (updates, comments, timeline), the downstream effect on status pages and reports, and that no alert rule is fired. The only mild redundancy is "cannot be undone," which restates destructiveHint. Missing are permission/auth prerequisites for such an irreversible operation.

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 dense sentence that front-loads the action and its cascade before the consequences. Every clause carries information (cascade scope, status page/report effects, irreversibility, alert behavior) with no filler or repetition of the title alone.

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 two-parameter destructive tool with full schema coverage and express annotations, the definition covers the essential unknowns: what else is destroyed, what downstream artifacts are affected, and that no notification fires. It falls short only on authorization requirements and confirmation/error behavior, and no output schema exists so return values need not be explained.

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 both project_id and incident_id are already documented, establishing the baseline of 3. The description adds only "by ID" and says nothing about the project scoping relationship or whether a foreign-project incident ID fails, so no meaning is added beyond the schema.

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 and resource ("Delete an incident by ID") and immediately scopes the cascade ("with its updates, comments and timeline"), which implicitly separates it from the sibling delete_incident_update. An agent can distinguish the whole-incident deletion from the single-update deletion without inspecting schemas.

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: "This cannot be undone" signals a high-caution operation, but there is no explicit when-to-use or when-not guidance, and no routing to alternatives such as recover_incident (soft resolve) or update_incident for non-destructive changes. The agent must infer the decision boundary from sibling names.

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