Cut transcript words

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

With no annotations, the description carries the full burden and does well: it discloses that the operation mutates the transcript, affects captions and rendered video, requires whole-word spans, returns specific fields, and can be reverted via review_transcript_flags. It omits failure behavior if the span does not cover whole words and any permission/auth context.

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 compact sentences, front-loaded with the action and effect, followed by return shape and undo guidance. Every sentence adds useful information with no repetition.

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 mutation tool with no annotations and no output schema, the description is largely complete: it explains the effect, return fields, and reversal path. The main gap is what happens when the span fails the whole-word requirement and whether there are other prerequisites.

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 100%, so the baseline is 3. The description adds a meaningful constraint beyond the schema by stating that startSec and endSec must cover whole words, which affects how the agent should choose those values.

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: 'Remove the words spoken between startSec and endSec from the transcript', and immediately explains the downstream effect on captions and rendered video. It also distinguishes its undo path from review_transcript_flags, making the operation identifiable against transcript-related siblings.

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 reversal route: 'Undo it by passing the flagId to review_transcript_flags with status rejected.' It also states the constraint that the span must cover whole words. It does not, however, compare itself to add_transcript_correction or say when to cut versus correct.

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