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

With no annotations, the description carries the behavioral disclosure burden. It discloses key behaviors: the private key never travels, words stay at the member tier forever and promotion doesn't make them the library's claim, and display_name is the only profile field. These are meaningful security and ownership traits, though the exact side effects of the drop (e.g., overwrite, create) are not stated.

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 three sentences, front-loaded with the step identifier. Each sentence adds distinct value: the action, the security property, and the ownership/schema constraints. There is no fluff or redundancy, making it concise and well-structured.

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 references the sibling workflow (shelf_signable) and provides security and ownership context, which is helpful. However, with no output schema and no return value description, it leaves out what the tool returns or errors on, and it doesn't fully explain the operational mechanics of the detached signature. For a mutation tool in a multi-step process, this is a notable 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?

The input schema has 0% coverage, but the description clarifies all three parameters: 'fields from shelf_signable' gives origin and meaning for the `fields` object; 'detached signature over those bytes' explains `signature`; and '`display_name` is the ONLY profile field' defines that optional property. This compensates well for the schema's silence, though it doesn't enumerate the fields within `fields`.

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 identifies this as 'Step 2 — stock the shelf' and instructs to 'Send the fields from shelf_signable plus a detached signature', indicating a submit/commit action for a shelf item. It distinguishes from the sibling tool shelf_signable by referencing it as the prior step, though the metaphor 'stock the shelf' is less explicit than a verb like 'submit'.

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 explicitly places the tool as 'Step 2' in a sequence, implying it should be used after shelf_signable. It provides context on the workflow (sign then drop) but does not explicitly state alternatives or when not to use it. This is clear usage guidance but lacks direct exclusions.

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