agent-receipts

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

With no annotations provided, the description carries full behavioral burden. It excellently discloses the return structure ('full receipt object including all 27 fields' with categorical breakdown), error behavior ('Returns an error message if the receipt ID does not exist'), and storage context ('local SQLite storage').

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 sentences, each earning its place: purpose declaration, return value details, error handling, and usage guidelines. Information is front-loaded with the core action, and no words are wasted.

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?

Despite no output schema, the description compensates by enumerating the 27 field categories returned. Error cases are covered, the single parameter is well-documented in schema, and sibling relationships are implied. Fully complete for a single-parameter retrieval tool.

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%, providing the receipt_id format ('rcpt_' + 12 alphanumeric characters). The description references the ID parameter ('by its ID') but does not add semantic meaning beyond the schema's detailed format specification. Baseline 3 is appropriate given the schema's completeness.

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 opens with a specific verb (Retrieve) + resource (receipt) + scope (single by ID from local SQLite storage). It distinguishes from siblings like list_receipts by emphasizing 'single receipt by its ID' and relates to verify_receipt by mentioning retrieval 'before verification'.

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?

Provides explicit positive guidance: 'Use to inspect a specific receipt or retrieve it before verification.' This establishes the primary use cases and hints at the relationship with verify_receipt. However, it lacks explicit negative guidance (when not to use) or explicit mention of list_receipts as the alternative for batch retrieval.

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