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

With no annotations, the description carries full behavioral transparency. It discloses idempotency ('already-absent fields report removed: false without rewriting the vault'), authentication requirements (nsec-signed kind-27235 or cached dpop_token), and destructive nature ('as destructive as a write'). This goes well beyond basic expectations.

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 concise yet dense, with four sentences each carrying critical information. It front-loads the core purpose and then provides necessary detail for a destructive operation without fluff.

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?

Despite no annotations, the description covers purpose, usage, idempotency, auth constraints, and destructive semantics. An output schema exists to document return values, so the description is complete for a security-sensitive mutation tool.

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 baseline is 3. The description adds meaningful context: 'field' is keyed on vaulted value, not template declaration, and 'dpop_token' is elaborated with proof details (nsec-signed kind-27235 or cached phrase). This adds value beyond the schema descriptions.

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 clearly states the tool removes a single operator secret field, using specific verbs like 'Remove' and 'Deletes one key'. It distinguishes itself from the sibling forget_credentials by explicitly naming it as the whole-row counterpart, and implies differentiation from delete_patron_credential by mentioning patron proofs are rejected.

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?

It provides explicit usage context: 'Use it to retire a leftover after an SDK cutover...' and contrasts with forget_credentials. It also clarifies exclusions by stating patron proofs are rejected, effectively indicating when not to use this tool. This meets the 'explicit when/when-not/alternatives' criterion.

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