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

The description adds real behavioral context beyond the annotations: the notary attests integrity and time but not correctness, only digests are stored (no floats in output), and verification works at two levels (offline L1, registry L2). The annotations already cover safety hints, so this is a genuine supplement. It does not mention that the call is non-idempotent, i.e. whether re-sealing the same output yields a new receipt, which is the one meaningful behavioral gap.

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?

Front-loaded with the core action and the return value, followed by the important trust-boundary caveat ('integrity and time, not correctness') and a spec pointer. Every sentence carries information; the only slightly awkward element is the trailing file-path reference, which assumes the agent can read local docs.

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?

An output schema exists, so return-value shape need not be described, and the L1/L2 verification model and trust boundary are well covered. However, for a tool with five parameters, nested objects, and no schema descriptions, the complete absence of parameter guidance leaves the definition short of what an agent needs to invoke it correctly.

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 description coverage is 0% across five parameters, three of them free-form nested objects ('output', 'subject', 'bindings') and one an array of strings ('excludes'). The description explains none of them: not what 'profile' selects, not what belongs in 'bindings' versus 'subject', not what 'excludes' removes from the digest. For a tool whose core semantics live in these objects, this is a substantial omission.

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 names a specific verb+resource pair: sealing an agent output as an "Outcome Receipt (ORC v0.1)" and registering its commitment. It distinguishes this from the notary's other operations implicitly by describing the receipt/registry duality. It falls short of 5 because the distinction from the sibling 'commit' tool (which also sounds like it registers commitments) is never made explicit.

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?

Usage is implied: you call this to seal an output and produce a verifiable receipt. But there is no explicit when-to-use versus 'commit', 'verify', or 'reveal', and no stated prerequisites or exclusions. The agent must infer the routing from the sibling names alone.

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