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 real value beyond that by clarifying what is actually destroyed (the finding record, not a code defect), which prevents a common misuse. It does not add rate limits, auth requirements, or conflict-retry behavior.

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 operation and required identifiers, followed by the semantic distinction and the alternative. No filler, every clause earns its place.

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 mutation with four required parameters, the annotations cover safety and the schema covers parameter mechanics, so the description only needs purpose, target semantics, and routing – all present. Only the response/conflict outcome and any dependent-data effects are left unaddressed, and there is no output schema to compensate.

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 the baseline is 3, but the description earns extra credit: the schema's own description for findingId is copy-pasted from projectId ('Owned project ID returned by list_linked_projects'), which is misleading, and the description correctly establishes findingId as the finding identifier while tying expectedVersion to the delete operation.

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 a precisely scoped resource (one owned finding), and immediately disambiguates the target from source-code defects. An agent can distinguish it from create_finding, update_finding, and list_findings without opening any schema.

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?

Names the alternative explicitly ('use update_finding to record a resolution instead'), giving a clear when-not-this-tool rule. It stops short of stating prerequisites such as ownership requirements or the need to re-read before retrying after a version conflict, which the agent must infer.

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