a11y-toolkit: WebVTT caption quality

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

Annotations already declare the read-only, idempotent, open-world, non-destructive profile, so the bar is lower. The description adds real behavioral context: it fetches and parses an external file, applies a concrete reading-speed standard (>21 chars/second, BBC/Netflix), and discloses a 'limits' field and the human-review boundary. It stops short of stating failure modes (e.g., unreachable URL, non-VTT content).

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?

The core purpose is front-loaded in the first clause, with detail following. It is dense and longer than typical, but nearly every sentence carries signal; the return-shape sentence is justified because there is no output schema. Slightly heavy parentheticals cost it the top mark.

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 no output schema, the description compensates by sketching the JSON return ({mode, cues, characters, captioned_seconds, findings, summary, limits}), states the analysis thresholds, the coverage condition, and the human-review limitation. An agent has everything needed to call it correctly and interpret results.

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 url, lang, and duration are already documented in the schema, including that duration enables the coverage check. The description's mention of the 21 chars/second threshold adds marginal color around the duration parameter but otherwise restates schema-provided meaning, so baseline 3 applies.

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 precise verb+resource: it downloads and parses the actual .vtt and judges caption quality (WCAG 1.2.2), enumerating what it inspects (timing lines, empty cues, overlaps, reading speed, coverage). It explicitly carves out its scope against the naive '<track> exists' check, so an agent can tell it apart from a presence-checking sibling without opening a schema.

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?

Clear context: pass the .vtt URL, and passing duration enables the coverage/completeness check, plus an explicit when-not ('not a substitute for human review of accuracy or speaker identification'). It never names a specific sibling tool as the alternative, so the routing is implied rather than explicit.

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