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

Annotations declare non-readOnly, idempotent, non-destructive, closed-world, and the description substantially extends them: no retranscription or billing, revision-conflict resolution ('rereading and reconciling the user edit'), word-alignment loss on text change, and the hard limit that rendered/quoted videos are untouched. Rich behavioral context beyond structured data.

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?

Five tight sentences, front-loaded with the primary action, then preconditions, then conditional payload rules, then edge cases. Every sentence carries distinct operational information with 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 and a complex nested payload with 4 required params, yet the description covers idempotency, optimistic-concurrency handling, alignment consequences, and the scope boundary of an already-rendered video. Nothing an agent needs to call this 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 description coverage is 0%, so the description must carry the load, and it does for the critical params: expectedRevision comes from get_subtitle_document, requestId must be fresh vs reused on retry, segments is complete-and-ordered and conditional on text/timing edits, wordIds must be preserved. It leaves documentId and the style fields (preset/position/color semantics) unexplained, so it doesn't fully compensate.

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?

Specific verb (save/edit) plus resource (owned subtitle revision) with scope qualifiers ('without retranscribing or charging'). It clearly separates this from the read-side sibling get_subtitle_document, which it names, so an agent can route without opening either 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?

Explicit when-to-do-what: 'supply the complete ordered segments array only when editing text/timing, otherwise style alone', plus retry guidance ('a fresh requestId for each edit; identical retries reuse that ID'). It blocks the wrong call shapes, but it never states when to prefer another tool (e.g. export or get) over editing.

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