ocr

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

With no annotations, the description carries the burden of behavioral disclosure. It states the tool is free, returns page count and cost, and does not run OCR. It doesn't explicitly mention side effects, but for a non-destructive estimation tool, this is adequate and adds relevant context beyond the schema.

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?

Two concise sentences that front-load the core purpose, then provide usage context. No wasted words; every clause adds value.

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 simple 2-parameter tool with no output schema, the description fully covers what it returns and when to use it. The note about large documents provides practical context. No gaps remain for the agent to understand 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 coverage is 100% (both params have descriptions). The tool description adds no additional parameter details beyond the schema, but the schema already explains url and pages. This meets the baseline 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 clearly states the tool's purpose: returning page count and exact cost_usd for reading a document via read_document, explicitly noting it does not run OCR. This distinguishes it from the sibling read_document by highlighting the estimation-focused, non-OCR scope.

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 guidance: 'Use before reading large documents.' This tells the agent when to invoke the tool, and the mention of 'without running OCR' implies a lighter alternative to read_document, effectively differentiating usage.

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

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

No annotations exist to carry the transparency burden, but the description discloses important behaviors: per-page pricing, billing to a specific account, response includes exact cost_usd and per-page citations, and support for limits. This goes beyond basic read-only intent.

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 three sentences with no filler. Every clause contributes new information: input type, output formats, pricing, response contents, pre-estimation guidance, and controls.

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 the 5 parameters and no output schema, the description gives a complete operating picture: input, output, cost behavior, cost guardrails, and the relevant sibling tool. It is sufficient for an agent to both select the tool and invoke it appropriately.

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 schema covers all 5 parameters, so the baseline is 3, but the description adds value by explaining cost implications ($0.00075/page), billing account, and the response containing cost_usd and citations. This clarifies the meaning and consequences of max_pages and max_cost_usd 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?

The description clearly identifies the action (read), the resource (document from a URL), and the output formats (markdown with tables preserved or plain text). It also distinguishes the tool from its sibling estimate_cost by framing reading as the downstream step after estimation.

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?

Concrete usage guidance is provided: use estimate_cost first for large documents, and make use of page ranges and hard spend caps. This explicitly tells the agent when to invoke a different tool and when to constrain this tool's costs.

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