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

Goes well past the destructiveHint/readOnlyHint annotations: items_replace fully REPLACES rather than merges, status is recomputed from items vs total, only the caller's receipt is reachable, and the call is PROPOSED-only returning status='confirmation_required' with action_id and plan_token until confirm_action is called. That is exactly the non-obvious behavior an agent needs before attempting a destructive edit.

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 dense sentences, front-loaded with purpose, then fields, then the replace semantic, then the confirmation protocol. The emphasis markers (REPLACE, PROPOSED, CONFIRMATION) are placed on the two facts most likely to cause a wrong call, and nothing is 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 10-parameter destructive mutation with no annotations beyond hints and no output schema, the description covers ownership scope, replace-vs-merge, derived status, and the two-step confirmation return shape. The remaining gap is partial-update semantics: it never states whether omitted fields are left unchanged, which matters for a patch-style endpoint.

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?

With 0% schema description coverage, the description carries the load and does so for most of the 10 parameters, adding real meaning: merchant_name is re-resolved, items_replace takes a full list matching add_receipt.items and replaces rather than appends, notes/category/payment_method are plain header edits. It does not explain the enum values, currency maxLength, the unit enums on line items, or the string|integer flexibility of receipt_id.

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?

Opens with a specific verb and resource -- fix a receipt by id -- and immediately frames the intended use case (recognition mistakes), then enumerates the editable header fields. An agent can tell this apart from add_receipt (items_replace references its items shape) and get_receipt/delete_receipt without opening any 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 a clear trigger ('fix ... recognition mistakes') and scopes reachability to 'the caller's own receipt'. It also routes the agent through confirm_action rather than expecting a direct write. It stops short of explicitly naming when to prefer a sibling (e.g. delete_receipt or a re-add) instead.

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