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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description still adds non-obvious behavior: the revocation cascades to every key the target delegated (implemented via a database trigger, not application code), takes effect immediately, and returns already_revoked rather than an error on repeat calls. This is exactly the extra context structured fields cannot carry.

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?

Three dense sentences, each front-loaded with actionable content: the operation and endpoint, then authorization scope, then the cascade side effect, then idempotency semantics. No filler sentences.

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 one-parameter mutation with no output schema, the description covers the essentials an agent needs: who may call it, the destructive cascade it triggers, and the exact response signal for an already-revoked key. Nothing material is missing.

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% and the single key_id parameter is fully described in the schema, including its source (tascan_list_delegations). The description adds no syntax or format detail beyond that, so the baseline of 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 (revoke) and resource (delegated child key), plus the concrete HTTP endpoint DELETE /delegations/:key_id. It is trivially distinguishable from its closest sibling, tascan_list_delegations, without opening either 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?

Gives explicit caller-eligibility rules — self-revoke, ancestor-key revoke, or org-admin session; all other callers are refused — which tells an agent exactly when this call will succeed. It stops short of naming an alternative tool to use for the disallowed cases, but the gating conditions are unusually concrete.

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