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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered; the description instead adds operational behavior the annotations cannot: pagination via nextOffset, passage granularity of roughly 30 seconds, null timestamps for text-only transcripts, and pause markers with source-second notation. The only gap is what happens when a transcript is missing or not yet complete, which is left unstated.

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?

Front-loaded with purpose and starting call, then pagination, then pause semantics, then the alternative tool — a sensible order with no filler sentences. The pause sentence is dense and the clause "as the answer's marks line says" is awkwardly self-referential, costing a bit of readability.

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 takes on return-shape duty and does explain passages, timestamps, pause marks, and nextOffset, which is the right coverage for a paginated read tool. Missing are failure modes (no transcript, transcript still processing) and any note on total transcript length, which would help an agent plan pagination.

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 only 25% (projectId alone is documented), so the description must carry the rest and largely does: it fixes the starting call (assetId, offset=0, limit=40) and clarifies the non-obvious unit that offset and limit count passages rather than words. assetId and projectId are left to the schema and the obvious, which is acceptable but keeps this short of a 5.

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 specific verb and resource ("Read a completed transcript") and immediately clarifies the unit of return: continuous text in timestamped passages, "not individual word rows." It also distinguishes itself from the closest sibling by naming read_analysis_range for per-word times, so an agent can separate the two 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?

Gives an explicit first-choice rule ("Use this first to understand a conversation or find interesting clips") and an explicit alternative with its selecting condition ("Use read_analysis_range with kind=transcript when you need every word's times around one cut"). It also states a negative scope ("Does not transcribe again or summarize"), which prevents misrouting to transcribe_asset.

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