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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the description earns credit for adding context beyond that: pagination, that boxes stay attached to their original observation, and that old exports only permit an estimated box timestamp. Those are genuine data-quality caveats an agent would not otherwise know.

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, both load-bearing, with the core capability front-loaded ahead of the caveats. The trailing clauses about box timestamps are dense and slightly cryptic, but nothing is padding.

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 return-value explanation is rightly omitted. However, with 7 optional parameters and no required ones, an agent needs to know which identifier must be supplied (slug, video_slug, or scene_id) and how the scoping works together; the description leaves that inference to the 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?

Only 29% of parameters carry schema descriptions, so the description must compensate. It does partially: 'video window' maps onto start_ms/end_ms and 'scene' onto scene_id. But it never clarifies the slug vs video_slug vs scene_id relationship, nor limit/cursor semantics, which leaves the three identifier parameters ambiguous.

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: 'Read paginated OCR text intervals', and scopes it to 'a video window or a scene'. This tells an agent exactly what is returned and the two possible scopes. It stops short of distinguishing itself from siblings such as get_transcript or get_scene, but the purpose itself is unambiguous.

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?

'Clipped to a video window or a scene' implies the choice of scope but never states when to pick each, nor when to prefer this over get_transcript or search_by_moment. Usage is inferable from the scope wording, not spelled out.

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