OCR a scanned/image-only PDF (Tesseract.js)

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

The description adds significant behavioral context beyond annotations: read-only nature, ~1-2s per page performance, optional dependencies for zero-cost markdown path, Tesseract.js license and pre-installation requirement, no outbound network calls. Annotations already declare readOnlyHint and idempotentHint, and description reinforces without contradiction.

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 detailed and informative, but somewhat dense. It front-loads the main purpose, which is good, but could be more structured (e.g., bullet points). However, every sentence adds value, so it earns a 4 rather than 5 for slight verbosity.

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 4 parameters and no output schema, the description is thorough. It explains the tool's role, performance, dependencies, installation, and fallback behavior. It describes return shape ('per-page text + per-page confidence + mean confidence + same shape as `obsidian_read_pdf`'), which compensates for lack of output schema.

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% with descriptions. The description adds extra meaning: default `lang` is 'eng', multi-lang via '+' with max 8 packs; `pages` is 1-indexed inclusive range; `scale` default 2 (~150 DPI), capped at 4, with performance trade-off. This enriches the schema significantly.

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 clearly states the tool runs OCR on image-only/scanned PDFs, with specific verb 'OCR' and resource 'image-only/scanned PDF'. It distinguishes from sibling `obsidian_read_pdf` by referencing the `has_text: false` return case, ensuring no ambiguity.

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 says 'Use this when `obsidian_read_pdf` returns `has_text: false`', providing clear context. Also mentions multilingual setup via `lang`, optional `pages` and `scale`, and fallback for missing language data, guiding proper invocation.

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