edit_recording

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

With no annotations, the description carries the full burden and does so: it discloses the required 'recordings:write' scope, the exact evaluation order of the operations, the original-timeline semantics of indexes and ms values, autoZoom's click-zoom behavior and Mac/Windows limitation, reversibility (Clipy keeps the original), transcript regeneration that replaces hand corrections, and share-link stability during re-render. This is unusually rich behavioral disclosure.

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?

Purpose is front-loaded and every sentence carries information — no filler. It is a dense block of run-on sentences without visual separation, which makes the ordering rule and caveats slightly harder to scan, but nothing is wasted.

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 10-parameter mutation tool with no annotations and no output schema, the description compensates thoroughly: auth scope, operation ordering, timeline semantics, reversibility, side effects on transcript/summary/key moments, and even the recommended pre-flight (dryRun plus user confirmation). The only implicit return detail, removedWords, is signaled well enough for an agent to proceed.

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 already 100%, so the baseline is 3, but the description adds meaning the schema cannot: it tells the agent where word indexes and ms timestamps come from (get_edit_transcript), that they are anchored to the ORIGINAL timeline, the ordering in which remove/restore operations resolve, and that dryRun should be used to preview removedWords. That is genuine semantic value beyond the field 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 ('Cut parts of a recording's video by its transcript') and immediately distinguishes itself from sibling mutators like replace_transcript and update_recording by scoping the edit to transcript-driven cuts. The parenthetical examples (fumbled sentence, tangent, dead air, filler words) make the intended use unmistakable.

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 a clear recommended workflow: run with dryRun first, show the user removedWords, and confirm before editing a recording others may be watching — plus a named dependency on get_edit_transcript for index sourcing. It does not explicitly compare itself against alternatives such as replace_transcript, so it falls short of a full when/when-not/alternatives statement.

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