overview

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

No annotations, so the description carries the burden. It does disclose non-obvious behavior: shot merging/splitting at pauses for the scenes level and offset-based paging for the shots level. It never states this is a read-only operation or what the response contains, leaving a gap for an annotation-free tool.

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?

Two dense sentences with the head concept front-loaded and no filler. The parenthetical clauses are information-bearing rather than padding, and it stays short despite covering two modes.

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 not be described, and the level/limit/offset behavior is covered. What is missing is any positioning against the eight sibling tools and any read-only confirmation for a tool with zero annotations.

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 0%, so the description must compensate, and it does: it defines the two meaningful values of level and explains that limit caps the scenes output while offset pages the shots output. Only video_id and the numeric defaults remain unexplained, but those are self-evident.

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?

Opens with a concrete metaphor ("Table of contents") immediately qualified by what each level returns: scenes merge similar shots and split long ones, shots enumerate s1..sN. An agent understands this lists the video's structural units. It does not, however, differentiate itself from siblings like index_video or peek.

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?

Usage is only implied through the level semantics (scenes = whole-video summary, shots = full enumeration). There is no explicit statement of when to pick this over index_video, peek, or query, and no exclusions or prerequisites.

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