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

With no annotations, the description carries the full transparency burden. It discloses idempotency (already-absent fields report `removed: false`), auth requirements (nsec-signed kind-27235 or cached dpop_token), and the destructive nature ('as destructive as a write'). It also explains the keyed-on-vaulted behavior, going well beyond a minimal statement.

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 front-loaded with a clear purpose, then uses exactly four additional sentences to cover distinctions, use cases, edge cases, auth, and destructive warnings. No filler — every sentence 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?

Given the tool's complexity (destructive, auth-gated, field-level vs row-level), the description addresses all critical aspects: what, when, auth requirements, idempotency, and return behavior (`removed: false`). Since an output schema exists, return-structure details are unnecessary. It is thorough for both new and returning agents.

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?

The schema already describes both parameters at 100% coverage, so the baseline is 3. The description adds extra semantic nuance: for `field`, it clarifies that stored-but-untemplated fields are first-class and deletion is keyed on what is vaulted, not template declarations. For `dpop_token`, it details accepted proof types and rejects patron proofs. This pushes it above baseline, though not to a 5 since it doesn't provide exhaustive parameter syntax.

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 opens with 'Remove a single operator secret field' — a specific verb and resource that clearly differentiates it from `forget_credentials` (which wipes the whole row) and other siblings. The focus on field-level deletion and the use-case example make the purpose unmistakable.

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?

Explicitly states it is the 'field-level counterpart to forget_credentials' and gives a concrete scenario (retiring a leftover after an SDK cutover) where this tool is preferred over full re-delivery. Also notes that patron proofs are rejected, which sets the audience boundary.

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