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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description adds genuinely new behavior beyond that: hashing is performed locally with no external call, and the hash is deterministic/recomputable by any holder of the same text. It does not discuss error cases (e.g. empty input), but adds real context over the annotations.

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?

Two sentences, no filler, front-loaded with the concrete result format before the explanatory property. Every clause earns its place.

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 single-input, no-output-schema, annotation-covered utility, this is complete: the 'sha256:<64 hex>' string in the description substitutes for the missing output schema, and the local/deterministic note closes the remaining behavioral 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?

One parameter with 100% schema description coverage ('the exact spec or output text to hash'), so the schema already carries the semantics. The description adds only 'the given text' and the note about exactness of the output format, which is marginal beyond the schema.

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?

States a specific verb and resource ('Computes the ... content hash of the given text') and pins down the exact output format ('sha256:<64 hex>') plus its role in INAM (specHash/outputHash). No sibling tool (search, receipts, reputation, whoami) does anything similar, so the agent can route unambiguously.

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 mention of specHash and outputHash implies the hash is meant to feed receipt verification, but the description never states when to call this versus the verify/check siblings, and gives no preconditions or exclusions. Usage is inferable rather than stated.

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