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 adds genuinely new behavior — fixed page size of 100 segments, millisecond timestamps, a readiness state field, and no on-demand transcription. Minor friction: it references 'nextSegmentOffset' while the input parameter is named 'segmentOffset', which could cause a moment of confusion when constructing the follow-up call.

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?

Three sentences, front-loaded with what is returned and how it is paged, then the readiness caveat, then the pagination instruction. No filler and nothing repeated from the schema.

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?

For a three-parameter read with no output schema, the description supplies the essentials: page size, timestamp units, readiness signaling, and the next-page mechanism. It would be stronger if it identified what 'id' refers to and how 'state' values other than 'not ready' should be interpreted.

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 all three parameters, and it only partially does — pagination behavior is implied for segmentOffset (via nextSegmentOffset) but the offset parameter is never named as an input, and neither 'id' (which identifier) nor 'platform' is explained. It adds meaning over the bare schema but doesn't close the gap.

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 the stored timed transcript of one Rumble video ad') plus concrete output shape (100 segments per page, start/end milliseconds). It does not explicitly differentiate itself from the nearest sibling, get_ad_evidence, but the purpose is unambiguous on its own.

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 clear operating context: the transcript must already exist ('nothing is transcribed on request'), 'state' signals not-ready, and pagination is via nextSegmentOffset. It stops short of naming an alternative tool to call when no transcript exists, leaving that inference to the agent.

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