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

With no annotations provided, the description fully carries the behavioral burden. It discloses idempotency (already-absent fields report 'removed: false' without rewriting the vault), the destructive nature ('as destructive as a write'), the proof requirements (nsec-signed kind-27235 or cached dpop_token), and the operator-only restriction. It also clarifies the field-keyed-on-vaulted-not-template behavior. This is comprehensive transparency.

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 well-structured and front-loaded with the core action in the first line. Each subsequent sentence adds essential context (use case, behavior, restrictions, idempotency, destructive nature). It is slightly verbose, but every clause earns its place. A minor reduction could tighten it, but it remains concise relative to the information conveyed.

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 (destructive operation, auth requirements, idempotency, field semantics), the description covers all necessary aspects. It explains what the tool does, when to use it, its behavioral guarantees, and its constraints. Since an output schema exists (indicated by 'Has output schema: true'), the description need not detail the return format. Nothing critical is missing for an agent 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?

Schema coverage is 100% for both parameters, so the baseline is 3. The description adds meaningful nuance beyond the schema by explaining that the delete is keyed on what is vaulted rather than the current template, which applies directly to the 'field' parameter. It also contextualizes the 'dpop_token' as the operator proof, though the schema already calls it 'Operator proof'. This added semantic depth justifies a 4.

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 states a specific verb ('Remove'/'Delete'), a precise resource ('single operator secret field'), and explicitly distinguishes it from 'forget_credentials' (wipes the whole row). It also differentiates from the sibling 'delete_patron_credential' by restricting to operator. This makes the purpose unambiguous and distinguishes it from nearby tools.

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 concrete use cases ('retire a leftover after an SDK cutover') and explicitly contrasts with the alternative 'forget_credentials' for full re-delivery. It also specifies the constraint that only operators can use it and that patron proofs are rejected, giving clear when-to-use and when-not-to-use guidance.

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