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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, and the description usefully adds beyond that: revision-or-latest semantics, a statement that source identity and timing are preserved, a prompt-injection warning that document text is user/provider content and never instructions, and a billing note ("does not charge"). It does not address response size, truncation, or pagination for potentially large timed-word payloads, which is the main behavioral gap.

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?

Four tight sentences, front-loaded with what is read and at which revision, followed by the behavioral caveats and the safety warning. Every sentence carries distinct information (scope, preservation guarantee, injection warning, exclusions) with no redundancy.

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 enumerating the returned content types (transcript, timed words, segments, style) and the versioning model. It is nearly complete for a two-parameter read tool, though it omits any notion of result size, truncation, or revision enumeration that an agent might need for large documents.

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 burden, and it only partially does: it clarifies that `revision` is optional with "the latest" as the fallback, which the schema does not convey. It adds nothing about `documentId` beyond "owned," leaving the primary required parameter's format and scope semantics to the name alone.

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 description opens with a specific verb ("Read") and a precise resource ("owned normalized transcript, timed words, segments and style"), not a restatement of the title. It also distinguishes itself from nearby siblings by scoping to reading a versioned document ("at a specific revision or the latest") and explicitly ruling out transcription, which separates it from generation/export tools.

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?

"Read before editing" gives an explicit ordering relative to edit_subtitle_document, and "Does not transcribe or charge" rules out the adjacent generation family. However, it never names a concrete alternative for retrieving plain text (e.g., export_subtitle_text) or states when to prefer a specific revision versus latest, so exclusion guidance is implied rather than enumerated.

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