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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive, closed-world), while the description adds substantive behavior: malformed blocks are skipped with a warning rather than failing the whole file, and hard failure conditions (no parseable cue, >2 MB input, shift beyond one hour) are spelled out. Return content — detected source format, cue count, warnings with line numbers, timing issues — is also disclosed.

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 operation and the 'contents not path' rule are front-loaded, and every remaining sentence carries a real constraint. It is a dense single block, though, and the enumerated return fields partly duplicate what the existing output schema already provides, which is mildly redundant.

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 annotations covering safety, full schema descriptions, and an output schema, the description still supplies the pieces structured data cannot: input size cap, failure modes, graceful degradation on malformed blocks, and unsupported formats with a pointer elsewhere. Nothing an agent needs to invoke it correctly is missing.

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% and already documents all three parameters well, so the baseline is 3. The description earns an extra point by adding constraints absent from the schema: the 2 MB input ceiling and the one-hour shift error condition, which give the caller limits the structured fields do not express.

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?

Names a specific verb and resource ('Convert subtitle text between SubRip (srt) and WebVTT (vtt)') plus the optional shift behavior, so the tool's scope is unmistakable. The siblings (aspect ratio, safe area, tempo, bitrate, social placements) are unrelated, so no disambiguation is needed and none is missing.

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?

Explicitly tells the caller to 'Pass the file contents, not a path', and defines an exclusion with a named alternative: 'ASS/SSA input is not supported here; the @prismposter/creator-tools package converts it.' This is exactly the when/when-not/alternative structure the dimension rewards.

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