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

With no annotations, the description carries the full behavioral burden and does well: it discloses the auth requirement (Last Price credential), the outcome-pricing refund behavior (a rejection within the outcome window refunds part of the cost, reflected in the result), and the downstream learning effect. It does not cover idempotency, retry/error semantics, or whether an outcome can be amended, which are notable gaps for a write tool.

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?

Front-loaded with the core action and the key parameter linkage, then layers in credential and refund caveats. Every sentence carries information, though the description packs several distinct concepts (feedback loop, refund behavior, auth) into a fairly dense block with no visual separation.

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 six-parameter tool with no output schema and no annotations, the description covers the essential linkage to compute_price, credential needs, and refund consequences. It is close to complete, but leaves the result shape (beyond refunds), error handling, and re-reporting behavior unaddressed.

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%, so the schema already documents all six parameters. The description's instruction to pass receipt.id as usage_event_id largely restates the schema's own wording, adding no new syntactic or format detail beyond it. Baseline 3 applies when the schema does the heavy lifting.

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 states a specific verb and resource (report whether a price from compute_price was used) and explicitly ties this tool to the output of the compute_price sibling. An agent can distinguish it from compute_price, verify_price, and pricing_conversation 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?

It tells the agent exactly what to pass (receipt.id from the compute_price result as usage_event_id) and constrains behavior with 'Report only what actually happened.' It gives clear positive context and purpose (feeding routing and confidence), but names no explicit when-not condition or alternative tool to prefer.

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