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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=false, but the description adds behavior the annotations cannot: a state gate (WORK_COMPLETED) and a per-call cost ('Platform fee CHF 0.05 per accepted call'), which is important spend context for a money-touching call. It stops short of describing the result of sealing or whether the pack becomes immutable.

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 tight sentences, front-loaded with the action and its precondition, then the exclusion, then the cost/sequence. Every clause carries information an agent needs; nothing is redundant filler.

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 mutating, money-charging tool with no output schema, the description covers the precondition, the sibling it is not, the fee, and the idempotency/quote flow. It does not say what the seal returns (e.g., seal id/hash) or whether sealing forecloses further evidence edits, which would complete the picture.

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 already 80%, so the schema carries most parameter meaning (flow_id, evidence, idempotency_key are all documented inline). The description adds dependency ordering the schema does not express: quote must be obtained first, then quote_id, mandate_token and idempotency_key are submitted together.

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 concrete verb pair and resource: 'Hashes and closes the proof pack after the work is completed.' It also pre-empts confusion with the invoice_issue sibling via 'Never: Issue the invoice,' so an agent can separate this from invoice_issue without opening either schema.

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?

Gives an explicit precondition ('Needs state WORK_COMPLETED'), an explicit exclusion ('Never: Issue the invoice'), and the required payment sequence ('quote first, then send quote_id, mandate_token and idempotency_key'). When-to-use, when-not-to-use, and the ordering prerequisite are all stated.

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