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

Annotations only carry readOnlyHint=false; the description supplies the context that matters: it is a HARD, non-undoable delete of derived markers rather than content, it does not affect footage length, and silence can be regenerated by re-transcribing.

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, each earning its place: what it deletes, what it does not affect, the sibling to use instead, and the undo/recovery caveat. Front-loaded with the action.

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?

A single-parameter deletion tool with only a readOnlyHint annotation. The description covers scope, side effects, reversibility, and the alternative, leaving nothing an agent needs to call it 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?

One parameter with 100% schema coverage, so the schema already documents project_id fully. The description adds nothing beyond it, which is the baseline for full-coverage schemas.

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 (delete) and resource ('[silence]' rows from the TRANSCRIPT), and immediately distinguishes itself from the sibling it is not: the footage keeps its length, so this is caption cleanup, not cutting.

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?

Names the alternative explicitly ('To cut the pauses out of the video for real, use remove_dead_air') and gives the condition that selects it. The recovery path (re-run transcription) is also stated.

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