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

Annotations already declare write, non-idempotent, open-world and non-destructive, so the baseline is lower; the description still adds real value by disclosing the pending/429 failure mode and the "no retry" policy, plus that the receipt is unlisted. It stops short of saying whether a pending result is recoverable or how to check status later.

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?

Four short clauses, leading with the action and its scope, then constraints and failure behavior. No padding and nothing buried.

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 one-parameter write tool with annotations covering safety traits and no output schema, the essential operational facts (unlisted, pending/429, no retry) are present. What is missing is any indication of what the caller receives back or how to distinguish a pending stamp from a completed one.

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% for the single parameter, so the description carries the burden. "hash-only" implies the hash identifies the content being stamped, but nothing explains what the hash is derived from or that it must be a 64-char hex digest beyond what the schema pattern enforces.

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?

"Explicitly create an unlisted hash-only receipt via createMoment" gives a concrete verb plus a precisely scoped resource, and "not an evaluation tool" fences off the evaluation use case. It never names the siblings first_at/verify directly, so the differentiation from those is inferential rather than stated.

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 signals the caller must opt in deliberately ("Explicitly"), rules out an adjacent use case ("not an evaluation tool"), and rules out a resource type ("No file upload"). No positive alternative is named, so the agent must infer which sibling to use when it does want evaluation or verification.

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