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

With no annotations, the description carries the full burden and does so richly: it discloses the proof-based access model, the exact signed message format, a security constraint (never send the key), and a privacy guarantee ('Nothing anywhere records who read what'). This is far beyond what structured data provides.

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 core purpose is front-loaded, then access semantics are layered in order of relevance. It is dense and the '[KEEP · internal]' prefix is noise, but every sentence adds necessary information rather than padding.

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 crypto-gated read with no annotations and no output schema, the description covers the authorization model thoroughly. It does not describe the shape of a returned shelf, but that gap is minor against the complexity it does address.

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 0%, so the description must compensate, and it does: viewer is the key, at is unix seconds, sig is a signature over a precisely specified string. Only 'member' (the required param) is left implicit, which keeps it just shy of a 5.

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+resource: 'Read one member's shelf.' It is immediately distinguishable from the write-side siblings (shelf_drop, shelf_signable) and from commons_read, and the reader knows exactly what object is being fetched.

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?

Gives clear conditional routing: an unproven caller sees only the promoted commons, while passing viewer/at/sig unlocks one's own rings or a friend's shelf ring. It doesn't name sibling alternatives explicitly, but the when-to-use conditions are concrete and unambiguous.

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