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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: the decoded size limit (≤ 10 MiB), the paid nature (~10 credits / $0.10), the payment method (prepaid key or x402), and the output shape (pages[].text and optional tables). It does not contradict annotations. A small gap is that it doesn't mention failure behavior for oversized PDFs, but the size limit is disclosed.

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 compact and front-loaded: the core action and resource appear in the first sentence, followed by routing guidance, input format, options, size limit, output shape, and cost. Every sentence earns its place, and the structure moves from what → when → how → constraints → output → cost. No filler or repetition of schema details.

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 tool's complexity (4 params, nested options, aliases, size limit, cost, output schema), the description covers all the essential context: what it does, when to use it, what inputs to provide, the size constraint, the cost, and the output shape. The output schema exists, so the description needn't detail return values beyond naming pages[].text and optional tables. An agent has everything needed to select and invoke this tool correctly.

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 parameters and aliases. The description adds value by clarifying the alias relationship ('file_base64 (or pdf/base64 aliases)') and the meaning of the options (includeTables / maxPages) in plain language. It also states the decoded size limit, which is a semantic constraint on file_base64. This goes beyond the schema's per-parameter descriptions, though the schema already does most of the work.

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 ('Extract'), a specific resource ('page text and heuristic tables from a base64-encoded PDF'), and the downstream purpose ('for downstream reasoning'). It also explicitly distinguishes itself from parse.receipt / parse.invoice, which are the closest siblings. An agent can tell this apart from extract.structured_data and extract.webpage without opening the 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?

The description gives explicit when-to-use guidance: 'Call for general PDF text hops' and explicitly excludes receipt/invoice field extraction by naming the alternatives parse.receipt / parse.invoice. It also states the input format (base64), size limit (≤ 10 MiB), and optional options. This is clear context with explicit exclusions and alternatives.

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