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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that by pinning the blast radius: it removes the stored investigation record specifically, not project graph nodes or local files. It still says nothing about whether the delete is recoverable, what happens to linked findings, or required permissions.

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?

Two sentences, front-loaded with the action and the two key identifiers, followed immediately by the scope limitation. Every clause earns its place and there is no filler.

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 destructive, version-guarded mutation with seven parameters, no output schema, and no annotations explaining conflict behavior, the description covers the resource scope adequately but omits recoverability, the effect on related records, and the retry/version-conflict workflow (left to the schema). An agent can call it correctly, but with some inference.

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 schema already documents all seven parameters, including idempotencyKey retry semantics and expectedVersion conflict behavior. The description only names investigationId and expectedVersion without adding format, ownership, or conflict-handling detail beyond the schema, so baseline 3 applies.

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 (delete) and resource (one saved investigation), plus a negative scope boundary ('not project graph nodes or local files') that separates it from graph-mutating siblings like clear_project_graph or patch_project_graph. It does not name a sibling alternative (e.g. delete_finding), but the scope is unambiguous.

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 implied by the verb and the boundary statement, which tells the agent this is not the tool for removing graph nodes or local files. There is no explicit when-to-use/when-not guidance, no mention of prerequisites such as reading the record first for expectedVersion, and no routing to delete_finding or delete_context_note for adjacent resources.

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