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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower, and the description adds real context: status packets attach contact sheets as images plus transcripts and detector tracks, and it discloses beta status plus quota/tier behavior (3 exports for free accounts, 2/day for trials, unlimited for subscribers). The quota details sit somewhat awkwardly on a read-only status tool but still inform the agent.

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?

It is a single dense paragraph that front-loads the purpose before the per-action breakdown, which is good structure. But it pads with tangential export-quota/tier details that do not help invoke this read-only tool, making it longer than the task requires.

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 five-action, seven-parameter tool with no output schema, the description covers action inputs but leaves return shapes largely unexplained (only the status packet is described) and explicitly defers exact schemas to video_guide. It is adequate but relies on another call to be fully actionable.

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 0%, so the description must carry the parameter burden, and it largely does: it maps each action to its required IDs (inspectionId, projectId, planId, assetId) and explains semantics like inUs/outUs as word-level speech timings and expectedRevision for framing. It falls short of 5 because the meaning of identifiers like inspectionId and targetId is still unexplained and additionalProperties is open.

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 the resource (Video Director evidence and plans) and enumerates five distinct actions with their required inputs, so an agent understands it is a multi-action inspection/planning tool. It does not clearly differentiate itself from close siblings like video_producer, video_projects, or video_jobs beyond deferring to video_guide, so it stops short of a 5.

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 gives one explicit routing instruction ('Call video_guide first for the catalog'), which is genuine usage guidance. However, it never states when to choose this tool over sibling tools such as video_producer or video_projects, so selection guidance is only implied rather than stated.

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