Run OCR

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the write/non-destructive profile is covered externally. The description adds nothing beyond that: it does not say whether the call enqueues an asynchronous job, whether it consumes credits (a recog_get_ocr_costs sibling exists), whether re-running overwrites existing transcripts, or how long it takes.

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?

A single front-loaded sentence with no filler. It is efficiently sized, though its brevity is a symptom of under-specification rather than of economy.

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?

For an 8-parameter, non-idempotent, non-read-only recognition action with no output schema, the description is far too thin. It omits the async job lifecycle, credit cost, transcript-replacement behavior, and how it relates to the ATR/HTR/TRHTR siblings, all of which an agent needs before invoking it.

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% across all 8 parameters, including non-obvious ones such as the deprecated 'id' alias, pages range format, ocrType default, and doBlockSegOnly. That is the baseline-3 case: the schema does the heavy lifting and the description contributes no additional parameter meaning.

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 states a verb (Run OCR) and a resource scope (a document or specific pages in a collection), so it is not vague. However, it essentially restates the name and title 'Run OCR', and it draws no line between this tool and the several sibling recognition tools (run_atr, run_htr_citlab, run_trhtr, text2image). An agent cannot tell from this text which recognition variant applies.

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?

There is no when-to-use guidance, no prerequisites (e.g. which collection/document states are eligible), and no mention of the alternative recognition endpoints that a caller would need to choose between. The single clause about documents vs. pages is scope, not selection guidance.

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