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

Annotations already declare readOnly/idempotent/non-destructive and openWorld, but the description adds material facts those annotations cannot: verification happens offline, the pass condition is byte-for-byte reproduction, and refetch_source triggers an outbound GET of the bound VergeCommon public record. The epistemic caveat that it proves reproducibility but not input truth, plus the 'Free rail' cost note, is exactly the kind of context annotations miss.

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, front-loaded with the action and the pass condition, with no filler sentences. It leans on terse jargon ('seal digests', 'Free rail') that an unfamiliar agent may need to decode, but nothing is redundant.

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?

With an output schema present, return values need not be explained, and the description covers the interpretive burden (reproducibility vs truth), network side effect, and cost. Remaining gaps are the receipt's expected structure and failure-mode behavior when a digest mismatches.

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% and 'receipt' is an opaque object with additionalProperties true, so the schema contributes almost nothing. The description partially compensates by naming the receipt's contents (input, result, seal digests) and by precisely defining refetch_source=true as reading the bound public record via GET only, but it never states the receipt's required shape or serialization for the byte-for-byte check.

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 plus the exact mechanism: 'Re-run a valuation receipt offline and check its input, result and seal digests,' with the acceptance criterion 'valid only if reproduced byte for byte.' It implicitly separates itself from valuation-producing siblings like value_site and explain_valuation, but never names a sibling to sharpen that boundary.

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 context is implied rather than stated: the tool is for reproducibility checks, and the caveat 'Shows reproducibility, not truth of inputs' tells the agent what conclusion it may draw. There is no explicit when-to-use/when-not guidance and no pointer to an alternative (e.g., explain_valuation for interpreting a valuation), so the agent must infer the routing.

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