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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety and side-effect profile is covered by structured data. The description adds value by disclosing the shape of the result (confidence, counts, suspicious flags) but says nothing about cost, pagination, or behavior for scans with no OCR results.

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, no filler: the first front-loads what is returned, the second gives the use case and parameter definition. Every sentence carries information an agent needs to select or call the tool.

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 enumerating return fields is technically redundant, yet it helps selection against the many sibling get_* tools. Between the annotations, the output schema and the parameter definition, the description covers enough for correct invocation; only edge-case behavior is unaddressed.

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% for the single parameter, so the schema offers nothing; the description compensates by defining scan_id as the UUID of a ScanMalware scan, which tells the agent both the format and how to obtain a valid value. It stops short of stating what happens for an unknown or non-OCR scan.

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 (get) plus resource (OCR text for a given scan) and it enumerates the returned substance: language, confidence, word and character counts, suspicious regions. This clearly separates it from aggregate siblings like get_ocr_stats and search-oriented siblings like search_ocr or search_ocr_pattern.

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?

The clause 'Useful when page text is drawn as images' implies the triggering condition, but no explicit when-not guidance is given and no sibling alternative (e.g. get_ocr_stats for aggregates, search_ocr for cross-scan queries) is named. Usage is inferable rather than stated.

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