pdfpeek: translate a PDF, digital or scanned, to English or 14 other languages as Markdown

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

Annotations declare read-only/idempotent, and the description still adds substantial operational detail: offline models, paragraphs-only, 10-page/30,000-character caps, 422/503 semantics with 'not charged', 3-30 s latency, USD 0.02 price with no free tier, no-logging guarantee, and an untrusted-output warning. This is rich context an agent needs beyond the safety annotations.

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?

Dense but front-loaded: purpose first, then output shape, limits, errors, pricing, and a security note. Nearly every clause carries distinct information, though the long single-block paragraph could be split for faster scanning.

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 and annotations cover the safety profile, so the description need not explain return values; it correctly focuses on limits, failure modes, latency, cost, and data handling. Nothing needed to invoke this 8-parameter tool correctly appears to be missing.

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%, so the baseline is 3; the description still adds cross-parameter meaning the schema lacks, such as the 30,000-character call limit, the source-must-be-given-for-scans rule, and confirmation that `target` controls the output language across a fixed 15-code set. Most remaining parameter detail is duplicated from 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 ('Translate a PDF document, digital or scanned ... as Markdown') with format and language scope, and explicitly distinguishes itself from the sibling translate_text for plain text. An agent can route between the two without opening a 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?

Names the alternative for plain text ('For plain text use translate_text') and gives a concrete usage condition ('Give `source` for a scan'). It does not cover when-not-to-use cases such as audio/URL-vs-base64 tradeoffs, but the routing context is clear.

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