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

Descriptions adds meaningful context beyond annotations: the extraction is heuristic, pricing is $0.01 per call, a prepaid x-credit-token header enables unlimited calls, one free call per day is available, and no wallet or API key is needed. No contradiction with readOnlyHint or idempotentHint.

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 purpose, followed by a usage constraint and operational details. The phrasing is compact and each sentence adds useful information, though the pricing/auth content makes it slightly dense.

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?

Given a single-parameter schema, rich annotations, and an existing output schema, the description covers purpose, required input, non-OCR constraint, and access/pricing. Nothing essential is missing for correct invocation.

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 already documents the 'text' parameter with 100% coverage, so baseline is 3. Description adds that text must be plain extracted text rather than a scan, which clarifies the expected format beyond the schema.

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?

States a specific verb and resource: 'Pull totals, IBAN, dates out of receipt text' and lists the exact extracted entities. The 'Not OCR' phrase distinguishes it from OCR-based sibling tools, so an agent can tell what it is and is not.

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 clear input conditions: 'Required input: text' and 'Not OCR — convert a scan to text first, then send it here.' This tells the agent when the tool is appropriate and how to prepare input, though it does not explicitly name alternative sibling tools.

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