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

With no annotations provided, the description carries the full burden and handles it well. It discloses that this is a write to a sensitive credential vault, requires proof of npub ownership, merges without affecting other fields, and is free. It does not detail failure modes or response behavior, but the presence of an output schema partially covers return 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 compact and information-dense: purpose, merge semantics, use cases, cost, authorization requirement, and sensitivity warning all appear in just a few short sentences. The most important scoping detail is front-loaded in the first sentence.

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 sensitive write operation with no annotations, the description covers the core behavior, preservation semantics, use cases, cost, and proof requirement, while the output schema handles return-value expectations. The main gap is the unresolved dpop_token semantics, which prevents full invocation confidence.

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. The description does not need to restate the clear npub, field, and value parameters. However, the dpop_token schema description is clearly erroneous — it says 'The value to store' — and the tool description only says 'Proof of npub ownership is required' without explicitly mapping that requirement to dpop_token. This leaves a meaningful parameter-semantics gap.

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 a specific verb phrase, 'Add or update a single patron credential field,' which clearly identifies both the action and the resource. The merge sentence further distinguishes it from delete or operator credential tools, so an agent can tell it apart from siblings like authority_delete_patron_credential and authority_update_operator_credential.

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 gives explicit, concrete use cases: setting an account identifier after OAuth and changing a default brain. It does not explicitly name alternatives or state when not to use the tool, but the use cases plus the 'single field' wording provide clear context for when this tool is appropriate.

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