find_text

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

No annotations, so the description carries full behavioral burden. It usefully discloses the return structure (t, matches with text/box/conf/row_box), but says nothing about fuzzy-match behavior, default limit, region semantics, or performance/cost. Partial disclosure.

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 compact sentences, front-loaded with the action and return type, followed by the one practical usage tip. No filler.

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?

No output schema, but the description compensates with an inline return shape, which is genuinely helpful for a 7-param tool. However, with no annotations and thin usage/routing guidance, the definition is not fully complete for correct selection.

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 71%, so most parameters are already documented there. The description adds nothing about fuzzy, limit, or region beyond the schema, though it does show row_box in the return when row=true. Baseline 3 for moderate schema coverage.

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?

States a specific verb+resource (locate text on the frame at time t) and even sketches the return shape. It does not distinguish itself from the sibling ocr_region, which an agent could reasonably pick instead, so it falls short of a 5.

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?

No guidance on when to use this versus ocr_region or track_text, and no prerequisites (e.g. video must exist, region vs full frame). The 'Use boxes for overlays' note hints at a downstream use but not tool selection.

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