agent-receipts

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

With no annotations provided, the description carries the full burden and successfully discloses return behavior: 'Returns an array... ordered by timestamp', specific fields included ('verdict, score, criteria results, and confidence'), and edge case handling ('Returns empty array if no judgments exist'). Missing only safety profile hints (read-only status) which would make it a 5.

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?

Five tightly constructed sentences with zero waste. Front-loaded with the core action, followed by linkage explanation, return structure, use cases, and edge case. Every sentence earns its place; no redundancy with the schema or title.

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 single-parameter retrieval tool without an output schema, the description comprehensively compensates by detailing the return array structure, ordering, contents, and empty-state behavior. It also explains the domain-specific parent_receipt_id concept. Minor gap: does not explicitly state the read-only/idempotent nature of the operation.

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?

While the schema has 100% coverage describing the receipt_id parameter, the description adds valuable semantic context by explaining the relationship mechanism ('Judgment receipts are linked via parent_receipt_id'), clarifying that the input is the original receipt ID, not the judgment ID. This domain context exceeds the baseline 3 for high-coverage schemas.

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') and resource ('judgment receipts'), clearly defining the scope as 'all judgment receipts associated with a given receipt ID'. It distinguishes itself from siblings like `get_receipt` (which gets a single receipt) and `judge_receipt` (which likely creates judgments) through explicit mention of the parent_receipt_id linkage and retrieval action.

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 clear positive use cases: 'Use to review the evaluation history of a receipt, compare multiple judgments, or audit AI quality assessments.' This contextualizes when to use the tool versus alternatives like `get_receipt` (for the receipt itself) or `judge_receipt` (for creating new judgments). Lacks explicit 'when not to use' exclusions, but the context is clear enough for selection.

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