document_scanner__scan_document

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

With no annotations, the description carries the full behavioral burden and does disclose non-obvious mechanics: PDFs are read from the text layer, images/scanned pages go through OCR, OCR languages default to Turkish and English. It omits whether the operation is read-only/non-mutating, whether tesseract.js must be installed, and what happens on unreadable files.

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, front-loaded with the detector scope and file types, followed by the parsing mechanics. No filler, no repetition, and each clause contributes distinct information.

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?

There is no output schema and no annotations, so the description should also orient the agent on what a scan returns (finding shape, severity, counts, error handling). It covers inputs and detection coverage well but says nothing about results, leaving the agent to invoke blind.

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 100%, so the baseline is 3; every parameter (path, ocr, include, languages) already has a description in the schema. The prose restates and lightly contextualizes the OCR/language behavior but adds no syntax, format, or default information the schema does not already carry.

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 ('Find PII... and credentials') plus concrete resource types (PDF, image, text file on disk) and a clear motivating context ('before it is given to an LLM'). The phrase 'on disk' implicitly separates it from document_scanner__scan_base64, but that sibling is never named, so differentiation is inferential rather than explicit.

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 context is implied by 'before it is given to an LLM', which tells the agent the intent, but there is no explicit when/when-not guidance and no routing to scan_base64 (for in-memory/base64 input) or list_detectors (to enumerate what can be found). The agent must infer the boundary.

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