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

Annotations indicate readOnlyHint=false and destructiveHint=false, but the description adds valuable behavioral guarantees: never overwrites the input in place, audio is carried along, and it returns the output path + duration. This goes beyond annotations and helps an agent predict side effects. It does not mention potential encoding/transcoding details, but the key safety and return behavior are disclosed.

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, front-loaded sentences, each earning its place: what it does, an example, audio behavior, return value, and non-destructive guarantee. No filler or repetition of schema text. Excellent structure for an agent to scan quickly.

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 tool with no output schema and moderate complexity, the description covers the return value (output path + duration), provides a concrete ranges example, and assures non-destructive behavior. It lacks explicit routing to sibling tools (e.g., video_concat) and details on edge cases like overlapping ranges, but is complete enough for correct invocation.

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 100%, so the baseline is 3. The description adds meaning beyond the schema by explicitly stating milliseconds, using an example for the ranges structure, and clarifying the new-file behavior. The output default and parent folder creation are already in the schema, but the example and unit clarification add value.

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?

The description uses a specific verb ('Trims a video'), names the resource, and specifies the core behavior: one or more time ranges in milliseconds, concatenated in order into a NEW file. This clearly differentiates it from siblings like video_concat, video_reframe, or video_export_gif. The example adds concrete clarity.

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?

The usage context is clear: trim video by keeping specified ranges and dropping dead segments, with the output as a new file. It provides a concrete example but does not explicitly contrast with alternatives such as video_concat or video_blur_region, nor does it state when not to use this tool. No explicit exclusions, but the context is sufficient.

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