Full video analysis

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: the execution flow, parallel transcript+keyframe processing, OCR step, and merged output composition. It does not mention latency or resource cost, which is notable for a tool described as 'most powerful one-shot', but this is a minor gap given annotation coverage.

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 sentences, each earning its place: pipeline overview (front-loaded first sentence), when-to-prefer routing, detail-parameter guidance, and the returns list. No fluff or repetition of schema content. For a 13-parameter tool this is tightly compressed.

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?

With no output schema, the description usefully enumerates what the tool returns. For a complex tool it covers the workflow, usage routing, and output composition well. The main completeness gap is parameter semantics for the several undocumented optional params, but those have sensible defaults and only `source` is required, so an agent can call it correctly with the information given.

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 31% (4 of 13 params documented), so the description must compensate for many undocumented parameters. It adds real usage semantics for `detail` (brief for lectures, detailed for demos) and hints at `inline_images` ('evenly spaced inline thumbs'), but leaves mode, start_sec/end_sec, max_frames, skip_frames, force_refresh, language, and skip_transcript unexplained. Compensation is only partial.

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 names a concrete multi-stage pipeline with explicit verbs ('resolve source → probe → transcript + keyframes → OCR → merged timeline'), and lists the exact return artifacts (summary, metadata, transcript, OCR text, frame paths, timeline, warnings). Calling itself the 'one-shot' comprehensive tool clearly differentiates it from siblings like video_transcribe, video_ocr, and video_extract_frames.

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 description gives explicit when-to-use guidance ('Prefer this when the user asks to watch, summarize, or understand a video') and even maps detail levels to task types (brief for long lectures, detailed for short UI demos). However, it never names siblings as alternatives or states when NOT to use this tool, so the exclusion logic is absent.

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