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

Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false; the description adds value on top: unsupported changes refuse rather than silently rebuild, operation_id must be preserved on retries, and the call consumes the account's direct-edit allowance at zero credit cost. It does not explain what 'destructive' means here (whether removed emphasis is recoverable via restore_version), which is the one gap annotations leave open.

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 with the action and its invariant, then prerequisites, side effects, retry rules, and cost in a compact sequence with no filler. Some clauses are telegraphic ('Unsupported changes refuse without rebuilding') and would read better as full sentences, but nothing is redundant.

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 6-parameter mutation with an output schema, the description covers what the agent must supply from elsewhere, that the result is a saved playable project, that file export is a separate call, refusal behavior, retry/idempotency discipline, and cost. No decision-relevant information 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 coverage is 67%, with add/remove carrying no descriptions in the schema; the description compensates by framing them as transcript word indices and by indicating that words and timing are untouched. It also clarifies the provenance of base_version and output_id (from get_project_context) and the retry contract for operation_id beyond the schema's own wording. It stops short of clarifying index-base or what happens if an index is already emphasized/unemphasized.

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 ('Add or remove emphasis on specific transcript word indices') plus the key invariant ('keeping the words and their timing'). That scope cleanly separates it from sibling mutators like cut_video_words (which deletes) and set_caption_style (which restyles).

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 prerequisite chain ('Read get_project_context first and pass its base_version and selected output_id') and routes the follow-up need elsewhere ('request a file separately with check_video with_download'). An agent knows both what to do before calling and where the file-export step lives.

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