transcript_delete

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

With no annotations, the description carries the full burden and does it well: it declares destructiveness, irreversibility, the exact cascade of deleted objects, the extra on-disk effect of delete_media=True, and the runtime precondition failure mode. This is far beyond what a bare 'delete' implies.

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 short sentences, front-loaded with the destructive/non-reversible warning, then consequences, then the parameter caveat, then the precondition. No sentence is filler.

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 no explanation. For a destructive mutation tool with zero annotation coverage, the description covers impact scope, side effects, and the precondition that would otherwise cause a failed call — nothing an agent needs is missing.

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 compensate. It fully explains the non-obvious parameter (`delete_media=True` also removes scratch audio on disk) and its default sense of being opt-in; job_id is self-evident, so nothing material is left ambiguous.

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+resource ('Delete a transcript') and immediately scopes it by enumerating exactly what is removed: the job, its segments, chunks, events and cached renders. This clearly separates it from sibling read tools (transcript_get, transcript_list) and from transcript_cancel, which it explicitly defers to.

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 when-not condition and the alternative action: 'Refuses while the job is running — cancel it first.' An agent knows to route to the cancel path first rather than attempting the delete and failing.

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