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

Goes well past the annotations: it discloses the cost model (text-layer pages free, OCR ~half a credit per page), the >20-page OCR confirmation flow via confirmation_required and confirm: true, the 300-page cap, and retry semantics where re-submitting the same files is free for already-read pages and only retries failures. The annotations only say readOnlyHint=false and destructiveHint=false, so this text carries the real behavioral load.

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?

Purpose and the import_script handoff are front-loaded, and no sentence is filler. It is dense, however: cost, confirmation, limits, and return-shape details are packed into one uninterrupted block, which makes scanning harder than it needs to be.

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, so the description supplies the return contract itself: textId, per-file pages read by text layer vs OCR, failedPages, the OCR spend of the call, and text chunked into 60000-character pages with nextOffset. Combined with the cost and confirmation rules, an agent has everything needed to call and re-call the tool correctly.

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%, so the baseline is 3, but the description adds operational meaning: confirm is tied to the user-agreed OCR estimate above 20 pages, and offset is tied to the returned nextOffset for paginated text. Remaining parameters (urls, projectId) are left to the schema, which already documents them.

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 specific verb and resource ('Turn files into text on the server') and immediately enumerates the accepted inputs: a PDF's text layer, OCR of scanned pages, page images in reading order, and plain-text files. It is unmistakable against siblings like import_script, edit_script, or view_media.

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?

Explicit routing: use it before import_script when a screenplay arrives as PDF or page images, then pass the returned textId to import_script; it also names a prohibition ('Never retype a long script with edit_script') and covers the non-screenplay case ('For notes and other documents, read the returned text'). Both the when and the when-not are stated.

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