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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=false), so the description's job is to add context. It does so meaningfully: credit consumption, a 25 MB size ceiling, accepted container formats, and language auto-detection. Auth requirements and latency/async behavior are still 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 purpose, then a compact Args block, then the cost and alternative routing in one line. Every sentence earns its place; the Args formatting is conventional and only mildly redundant with 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?

An output schema exists, so return values need not be explained. Parameters are fully described despite 0% schema coverage, and the annotations plus the credits/alternative notes give the agent everything needed to decide and invoke correctly.

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 coverage is 0%, so the description carries the full parameter burden and does so: audio_url is constrained to public http(s) URLs with a size limit and format list, and language is documented as an optional ISO 639-1 hint that is auto-detected when omitted. This fully compensates for the empty schema descriptions.

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 ('Transcribe speech in an audio or video file to text') and names the sibling it is not (youtube_transcript) for a distinguishable case. An agent can tell it apart from youtube_transcript 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 routes YouTube links to youtube_transcript, which is the key routing decision among the siblings. It also warns that the call spends Audexum credits, giving the agent a cost-based usage consideration rather than leaving it to inference.

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