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

With no annotations, the description carries the full burden, and it delivers: it discloses proof-based authorization, the visibility boundary for unproven callers, the exact signature payload, and the privacy property that no read is recorded. This goes well beyond the schema and materially shapes expectations for using the tool.

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?

Three dense sentences, each earning its place: the action, the authorization model, and the authentication recipe. The most important fact (what the tool does) is front-loaded, and the security-critical signing detail is placed where it directly supports invocation.

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 4-parameter tool with no output schema and no annotations, the description provides everything needed to invoke it correctly: required parameter, optional auth parameters, exact signature construction, and behavioral expectations. The absence of a documented return shape is acceptable because the schema provides no output contract and the read action is well scoped.

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 description coverage is 0%, so the description must define the parameters, and it does: member is the target shelf, viewer is a key, at is unix seconds, and sig is a signature over a precisely specified string. It even explains why these parameters are needed and warns the agent not to send the secret key.

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 and resource: "Read one member's shelf." It further distinguishes the tool from sibling read-type tools by emphasizing proof-based access rather than key-based naming, and by contrasting the unproven caller's view (promoted commons) with private/friend shelf access.

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 clear conditions of use: no proof means only promoted commons are visible; to read one's own rings or a friend's shelf ring, the caller must pass viewer, at, and sig. It does not name alternative sibling tools explicitly, so it stops short of full when-not-to-use guidance, but the access rules are unambiguous.

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