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

Annotations only cover the safety profile (readOnly, idempotent, openWorld, non-destructive); the description goes well beyond that with pricing (0.01 USDC/page, 0.2 USDC cap, upto behavior), async job semantics with jobId/pollUrl, and p95 latency of ~10000 ms. It also discloses hard functional limits (no OCR, no password-protected files, 15 MB ceiling) that an agent cannot infer from structured fields.

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?

Information-dense with no filler, and each sentence carries a distinct fact (return shape, usage, exclusions, cost, async contract). It opens with the return value rather than the core action and the pricing/async clauses are packed, but nothing is redundant.

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?

An output schema exists, so return values need not be explained, yet the description still summarizes them helpfully. Combined with cost, latency, async polling contract, size cap and the three unsupported-input cases, an agent has everything needed to decide and to call 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?

There is a single parameter and schema description coverage is 100%, so the schema already documents the URL format and the 15 MB limit. The description repeats the size constraint but adds no new parameter-level syntax or format detail. Baseline 3 is appropriate 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?

Specific verb+resource ('Returns JSON with the text of each page of a PDF... plus title, author and producer metadata') with concrete scope (first 20 pages). It is clearly distinguishable from the polling sibling pdf-text_v1_status because the description states the paid call returns a jobId and a separate pollUrl.

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?

Explicit positive trigger ('Use when you need to extract text from a pdf for document parsing, search or an LLM and can poll an async job') and explicit exclusions ('Do not use when the PDF is scanned (no OCR), password protected or over 15 MB'). The polling requirement effectively names the alternative path (pollUrl / status sibling).

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