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

The description contradicts the annotations: it says 'Update' while destructiveHint is true and the tool name indicates deletion, which is a direct contradiction. It also adds no meaningful behavioral detail beyond the annotations—'privacy-filtered project metadata' is ambiguous and unexplained.

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?

The description is a single sentence, but it is not appropriately structured: it is under-specified and fails to front-load a clear purpose. The garbled phrasing makes it more of a hindrance than a concise, helpful summary.

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, idempotent tool with 7 parameters, 4 required, nested objects, and no output schema, the description is wholly inadequate. It does not address required fields, idempotency semantics, expectedVersion meaning, or what the tool does with the investigation—leaving agents unable to invoke it correctly.

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?

With 0% schema description coverage, the description must compensate by explaining the parameters, but it does not mention projectId, investigationId, idempotencyKey, expectedVersion, or the nested details object. The vague 'privacy-filtered project metadata' adds no semantic value to 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?

The description 'Update hosted delete investigation using privacy-filtered project metadata' is confusing: the verb 'Update' conflicts with the tool name 'delete_investigation', and the phrase 'hosted delete investigation' is not a standard concept. It does not clearly state that the tool deletes an investigation, and it fails to distinguish this from siblings like save_investigation or delete_finding.

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 description provides no guidance on when to use this tool versus alternatives such as save_investigation or list_investigations, nor does it mention prerequisites, conditions, or exclusions. An agent is left without any context to select this tool appropriately.

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