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

With no annotations, the description carries full burden and does disclose useful traits: the private key never travels, and words remain at the `member` tier permanently even if promoted to the commons. However, it says nothing about the write's return, idempotency, or error behavior, leaving operational semantics uncovered.

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?

It is front-loaded with the step label and the core instruction, then appends ownership policy. Most sentences earn their place, though the tier/commons sentence is dense and slightly tangential to 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 an internal tool with a nested object param, no annotations, and no output schema, the description links the workflow and identifies parameters but omits what a successful drop returns or how failures surface. Adequate but with a clear gap for a write operation.

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 addresses all three parameters: `fields` sourced from shelf_signable, `signature` as a detached signature "over those bytes," and `display_name` as "the ONLY profile field there is." It adds meaning and constraints but not encoding/format detail.

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?

"Step 2 — stock the shelf" plus "send the fields from shelf_signable plus a detached signature over those bytes" conveys a concrete submit-signed-data action and explicitly links it as the follow-on to shelf_signable step 1. The metaphor "stock the shelf" is less plain than a literal verb, but the sibling differentiation from shelf_signable/shelf_read is clear.

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 tells the agent exactly when to invoke it: after producing the signature, sending "the fields from shelf_signable plus a detached signature over those bytes." That is a clear workflow precondition, though it never states when NOT to use it or names an alternative path.

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