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

With no annotations, the description carries the full burden and does well: it discloses auth requirements per action, the append-only nature ('acts are appended, never replaced'), and the precise side effect of a refusal (withholds amplification only; the drop stays on the member's own shelf). It does not describe the success response or failure/error behavior, which leaves a gap for a mutation tool with no output schema.

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?

Dense but front-loaded: the action list comes first, then the reason invariant, then the authorization matrix. A few clauses ('a refusal without a reason teaches the community nothing') are rationale rather than instruction, which is slight padding for a definition this compact.

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 7-parameter, nested-object, no-output-schema mutation tool, the description covers authorization, action semantics, immutability, and the refusal side effect. It omits return/confirmation behavior and error conditions, the main remaining completeness gap.

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 only 43%, and the description compensates substantially by mapping credentials to actions (token for promote/refuse; fields+signature for withdraw), naming the three valid action values, and clarifying that steward is a name rather than authority. It still leaves card_id and the exact shape of the nested fields object to the schema, so it is strong but not exhaustive.

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States a specific verb and resource: it records one act (promoted / refused / withdrawn) on a single drop, and names the sibling (curate_signable) it is not. An agent can distinguish it from curate_queue and curate_signable without opening any 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?

Explicitly routes by action and actor: promote/refuse require the steward token, withdrawing your own card requires fields+signature from curate_signable instead. It also states the invariant that a name plus a reason is always required, and warns that a typed name is not authority.

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