track_text

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

No annotations are provided, so the description carries the full burden. It does usefully sketch the return payload ({query, spans:[{t0,t1,box_start,box_end,moved}]}), which is real information given there is no output schema. But it says nothing about cost, sampling behavior, permissions, or what 'moved' means.

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 line with zero padding, so nothing is wasted and the time-range constraint is front-loaded. But the compression is excessive enough that clarity is lost, which is under-specification rather than true conciseness.

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?

With 7 parameters, no annotations, no output schema, and 43% schema coverage, the description is the only source of behavioral and parameter context and it delivers only a partial return sketch. An agent cannot reliably call this tool correctly without guessing at step, fuzzy, region, and the meaning of the returned fields.

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 only 43%, so the description must compensate for step, fuzzy, region, video, and query. It only reinforces t0/t1 and query, adding no format, range, or default details for the undocumented parameters. The gap is left unfilled.

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 notation 'When/where text is visible in [t0,t1]' conveys a temporal+spatial text tracking operation, which is distinguishable from find_text and ocr_region. However it is written in cryptic pseudo-notation rather than a plain verb+resource statement, so an agent must decode it. The '->' return sketch hints at the resource but never names it explicitly.

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 guidance on when to choose this over find_text, ocr_region, or chart_extract, all of which involve text detection. No exclusions, prerequisites, or context of use are given. The agent must infer selection from the name alone.

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