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

Goes beyond the annotations by disclosing the engine (Tesseract), the expected latency (30-90 seconds), and the shape of the result (a new PDF with an added text layer rather than an in-place edit). This is useful context that the readOnly/destructive hints alone don't convey. It still doesn't say what happens on failure or how the output file is returned.

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 sentences, zero padding: the first defines the operation and its output, the second gives the trigger and the latency. The purpose and the when-to-use are both front-loaded.

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?

With no output schema, the description carries the return-value burden and does so by naming the searchable-PDF result, plus timing expectations. The only real gap is the unexplained lang parameter and any input constraints, but for a straightforward single-operation tool this is nearly complete.

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 67%; 'file' and 'filename' are documented, but 'lang' has no schema description and the description never mentions language selection. The description adds no parameter-level detail, so the undocumented lang parameter remains opaque. Baseline 3 is appropriate given partial schema coverage.

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 ('Run OCR over a scanned PDF') plus the exact output ('searchable PDF with an added text layer') and names the engine. An agent can distinguish it from pdf_extract_text, which reads text rather than producing a searchable file.

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?

Explicitly gives the triggering condition: 'Use this when the user asks to make a scanned PDF searchable or extract text from scans.' It doesn't name a when-not case or point to a specific alternative sibling, but the scanned-PDF qualifier implicitly separates it from pdf_extract_text.

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