ocr

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

Annotations declare a write operation (readOnlyHint=false) that is non-destructive and closed-world, and the description meaningfully extends this: it discloses the skip-existing-text rule, the force override, page straightening, and confidence reporting. Gaps remain around the overwrite parameter (what happens to an existing output file) and whether the source PDF is mutated or a new file is written.

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?

Three tight sentences: what it does, the language-code format, then the skip/force rule. Front-loaded and every clause carries information; zero filler.

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 details need not be spelled out, and the description still flags the confidence report. However, for a 6-parameter mutation tool it leaves `pages`, `output`, and `overwrite` semantics unexplained, which an agent needs before invoking safely.

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 0% across 6 parameters, so the description carries the burden. It gives genuinely useful semantics for `language` ('fra', 'eng', 'fra+eng', 'auto') and for `force`, but says nothing about `path`, `output`, `pages` (range syntax), or `overwrite`, leaving four parameters undocumented in both schema and description.

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+resource ('Make a scanned PDF searchable with Tesseract') and adds the mechanism and side behaviours (deskew, confidence reporting). No sibling tool performs OCR, so read_text/replace_text/render_page are implicitly excluded by the 'scanned PDF' framing.

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?

Usage is implied rather than stated: the tool is for scanned PDFs, and 'Pages that already have text are skipped unless force=true' tells the agent when to set force. But it never says when to prefer this over read_text or export, nor what prerequisites (e.g., Tesseract availability) apply.

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