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

With no annotations, the description carries the full burden and mostly discharges it: it discloses that url content is opened once in an "airlock," only a waybill (title, size, sha256, timestamp) is kept, bytes are discarded, and nothing is embedded to avoid leaking a reader's IP. It also discloses the ring gating behavior (shelf is ungated, commons awaits a steward). It omits any explicit auth/permission or rate-limit statement, so it is not fully transparent.

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?

Purpose and return shape are correctly front-loaded, and the ring/url sentences earn their place. But the prose is heavy with rhetorical capitalizations ("WAYBILL," "AMPLIFIES," "covenant key") and the closing aphorism about gates adds atmosphere rather than actionable information, so it is larger than it needs to be.

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?

The description explains the return shape, the ring behaviors, and the url handling, which is substantial given there is no output schema. The notable gap is that being "step 1" implies a follow-up (shelf_drop) to submit the signed payload, but that next step is never named, so the workflow is left partly implicit.

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 a moderate 75%, and the description genuinely compensates: it explains that url applies only to kind=link and why the body is still required ("a bare link is not curation"), defines member as your public key, and gives per-ring meanings for ring beyond the bare enum values. It leaves subject and attribution largely unelaborated, keeping it below 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?

The first sentence gives a specific function: it returns {fields, signable}, the canonical bytes to sign to author a card on your shelf, framed as "step 1 of stocking your own shelf." That is a clear verb+resource and a distinct role from CRUD siblings like cards_browse or shelf_read. It stops short of 5 because it never differentiates itself from the other *_signable siblings (curate_signable, mesh_signable, playbook_signable, moderation_signable), leaving the agent to infer which signing pipeline it wants.

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?

It supplies real when-to-use context through the ring semantics: private (only you), shelf (you plus friends who chose you, ungated and live on signing), commons (site-wide, waits for a human steward). That tells the caller the consequence of each usage mode. It does not, however, name a sibling to prefer or state explicit exclusions, so it falls short of a 5.

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