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

Annotations already cover the safety profile (destructiveHint=true, idempotentHint=true, readOnlyHint=false), so the bar is lower. The description adds valuable non-structured context: it can consume account credits, it preserves the other clips (blast radius), and it advises reading current state before retrying. Missing only details like whether the replaced source can be recovered.

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 tight sentences, front-loaded with the operation and mechanism before cost and retry caveats. No filler, though the credit and retry notes are compressed to the point of mild ambiguity.

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, but with 13 parameters at 15% schema coverage and a credit-spending mutation, the description leaves several parameters unexplained and gives no detail on the auto_best mode or the layout/content hints. Adequate for the main path, thin for full complexity.

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 only 15% across 13 parameters, so the description must carry meaning. It maps well to selectionMode (suggestion/time_range) and suggestion/time params, but leaves layoutMode, contentTypeHint, captionsEnabled, min/maxDurationSeconds, lookId, workspaceId, and idempotencyKey entirely undocumented. Partial compensation only.

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 ('Replace the source moment for one managed clip') plus the two mechanisms ('verified suggestion or explicit time range'). This clearly separates it from siblings like clips_create, clips_get, and clips_repair without needing to open any schema.

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?

It implies the usage path via 'using a verified suggestion or explicit time range' and gives a retry prerequisite ('read current state before retrying'), but never states when to prefer this over clips_create, clips_repair, or clips_recover, nor any when-not condition. Usage is inferable rather than explicit.

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