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

Annotations already declare readOnlyHint and idempotentHint true, safely indicating a non-destructive operation. The description adds valuable context by detailing what the receipt contains (e.g., 'ready-made citation line') and provides a behavioral instruction ('Omit code for every attribute's receipt'), which goes beyond the schema. This enriches the agent's understanding without contradicting the annotations.

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?

The description is compact at two sentences, efficiently packing key details about the return contents. However, the second sentence 'Omit code for every attribute's receipt' is slightly awkward and could be clearer, though it's not verbose. Overall, it's well-structured with no wasted words.

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 read-only, idempotent tool with a straightforward purpose and an output schema available, the description sufficiently conveys the tool's behavior and result composition. It explains what the receipt includes and gives a usage hint. While it could mention potential edge cases or error conditions, it's adequate for a utility of this simplicity.

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?

The input schema already documents all three parameters (id, code, project_context) with descriptions, achieving 100% coverage. The description's phrase 'Omit code for every attribute's receipt' aligns with the schema's instruction for the 'code' parameter, adding no new information. Per the rubric, with high schema coverage, the baseline of 3 is appropriate; the description does not significantly enhance parameter understanding.

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 clearly states that the tool returns the receipt behind a stated value, specifying exact components like verbatim source quote, page, extraction method, and SHA-256 hash. This specificity distinguishes it from sibling tools like get_part (which retrieves part data) and search_parts (which searches), making the purpose and scope unambiguous.

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?

The purpose of fetching provenance is implied by the description and title, so an agent might infer when to use it. However, there is no explicit guidance on when to use this versus alternatives, no exclusions (e.g., when not to use), and no mention of relationships to sibling tools like compare_parts or list_builds. It briefly instructs to omit 'code' for all attributes, which serves as a usage hint, but it's not elaborated.

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