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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so safety is covered. The description adds genuinely new behavioral context by stating the operation costs $1 USDC, but the payoff sentence ('an object with 29 fields including amount_field, artefact_count') duplicates the output schema rather than explaining the grading behavior or what the grade means.

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?

Three run-on fragments crammed into two lines, mixing purpose, sibling routing, return-field enumeration and pricing with no front-loading or sentence structure. The backticked tool name mid-sentence and the trailing '$1 USDC' read as appended metadata rather than prose.

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 values needn't be explained, and annotations carry the safety profile. What's missing is the substantive piece: with two optional parameters (including an unbounded nested `record`), the description never says what input is actually required to run a grading, nor what the grade or the amount_field/artefact_count drive.

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 both parameters are documented structurally and the baseline of 3 applies. The description adds nothing about how `record` and `dispute_id` relate or which one to supply — a real ambiguity given both are optional and `record` is a free-form nested object.

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 pair ('Assemble and grade the evidence') and names the sibling `build_dispute_counterparty_record` as the wrong tool for this job, which lets an agent separate the two without opening schemas. The resource is only named indirectly via the sibling contrast rather than stated plainly as dispute evidence, which keeps it from a 5.

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 explicitly routes the agent: use this for dispute evidence, not the dispute counterparty record. That is a real when-to-use/when-not pairing against a concrete alternative, though the phrasing is garbled and it gives no prerequisites or ordering relative to the other dispute tools (create_dispute_ruling, verify_dispute_ruling, ingest_evidence).

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