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

Annotations declare destructiveHint=true, idempotentHint=true, readOnlyHint=false, and openWorldHint=false. The description adds no behavioral context beyond the annotations. It does not explain that deletion is permanent, that expectedVersion is used for optimistic concurrency, that idempotencyKey ensures safe retries, or that the operation is destructive. The phrase 'frozen Brain Scanner policy' hints at constraints but is too vague to be useful.

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, so it is concise, but it is not well-structured for an agent. It front-loads the phrase 'closed record delete capability family' which is vague, and the reference to 'frozen Brain Scanner policy' is unexplained. The sentence earns its place only partially; it conveys that this is a delete operation family but does not provide actionable information.

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?

Given the tool's complexity (three operation variants, nested payloads, required idempotencyKey and expectedVersion, destructive behavior) and the absence of an output schema, the description is severely incomplete. It does not mention the three distinct operations, the need for idempotency keys, version checking, or the destructive nature of the operations. An agent would struggle to invoke this tool correctly without opening the schema and guessing at semantics.

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%, so the description must compensate for the schema's lack of parameter documentation. It does not. The schema shows three operation variants with payloads containing projectId, noteId/findingId/investigationId, idempotencyKey, expectedVersion, and optional details, but the description explains none of these. An agent cannot infer which operation to choose or what the parameters mean from the description alone.

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 says 'Use the closed record delete capability family from the frozen Brain Scanner policy.' It identifies a verb (delete) and a resource family (records), but it is vague about what specific records are deleted and does not distinguish among the three operations (delete_context_note, delete_finding, delete_investigation) encoded in the schema. The phrase 'closed record delete capability family' is jargon-heavy and does not clearly state what the tool does for an agent.

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. It mentions a 'frozen Brain Scanner policy' but does not explain what that policy implies or when deletion is appropriate. Sibling tools like delete_context_note, delete_finding, and delete_investigation exist as separate tools, but the description does not clarify when to use this family versus those individual tools or other deletion-related tools like archive_context_note.

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