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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond the annotations: that the call incurs no charge and will not start or retry work, which matters given the billing-adjacent siblings in this toolset.

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 short sentences, zero filler, with the core action and the prerequisite front-loaded before the prohibitions. Every sentence earns its place.

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?

An output schema exists so return values need not be described, and the prerequisite plus cost behavior are stated. The only gap is that the required 'media' argument shape is left entirely to the schema, but for a two-parameter read tool this is close to complete.

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 50%: chunk_max_seconds carries a detailed schema description, while the required 'media' parameter (an anyOf over upload_id/generation_id) has none. The description adds no parameter meaning at all, so the agent must rely on the self-describing const/format structure of the schema to supply the media argument.

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 transcript and status') and immediately scopes it against the sibling that produces the data ('Call transcribe_media first'). An agent can distinguish this read tool from transcribe_media 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?

Explicitly names the prerequisite (transcribe_media must be called first) and states the negative cases ('Never starts, retries or charges a transcription'), which is exactly the when-not guidance needed to prevent misuse of a read tool as a generation trigger.

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