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

With no annotations, the description carries the full burden and does well on the money dimension: it states the exact cost ($0.02 USDC on Solana), that the payment buys exactly one report check, and that the output is signed. It also pre-empts a likely misconception by declaring 'Counts per type only; no composite score', which is real behavioral disclosure. Missing are what happens on invalid input or failed grading (is the fee still charged?), and how the signature can be verified.

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?

A single dense sentence with zero filler, and the pricing hook is front-loaded where a paying agent will see it first. The enum-style clause is terse but informative rather than decorative. Slight readability cost from packing price, input roles, and both output taxonomies into one sentence.

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?

There is no output schema, so the description must describe returns — and it does, enumerating both claim classes and their verdict labels plus the aggregate rule. For a nested-object, three-parameter tool this is close to sufficient. The remaining gap is operational: no statement of what a signed report looks like, how to verify it, or what failure responses cost.

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 100%, so the baseline is 3. The description clarifies which artefact is graded against which — the report's typed claims against the transcript and evidence — but the schema already says evidence is what Class B claims are graded against, so the added meaning is marginal. It never explains why 'evidence' is optional when Class B grading appears to depend on it.

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 gives a specific verb and resource: it grades a report's typed claims against a submitted transcript and evidence and returns a signed correspondence report. The exact output vocabulary (Class A: PRESENT / ABSENT / FOUND-AS-VARIANT; Class B: PRESENT-AND-MATCHING / PRESENT-BUT-DIFFERS / ABSENT) makes the operation unambiguous. It does not name its siblings artefact_correspondence_criteria or artefact_correspondence_precheck, so the stage it occupies in that three-tool family is left implicit.

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?

Nowhere does it say when to call this instead of artefact_correspondence_criteria or artefact_correspondence_precheck, nor whether a precheck or criteria fetch is a prerequisite. A reader can infer that this is the paid execution step, but the inference comes from the price line, not from stated guidance. No exclusions or failure conditions are given.

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