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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'Free, read-only' is partly redundant. However, the description adds real value beyond the annotations: unit conventions (times in seconds), the freshness warning that the editor may have changed the project, and a hint that the payload carries ids usable for subsequent ops.

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?

Front-loaded with the purpose, then usage guidance, then a short safety note. Every clause earns its place, though the parenthetical unit/format note is slightly dense and 'Free, read-only' partially duplicates the annotations.

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?

Despite an output schema existing, the description usefully summarizes the return payload and the freshness caveat an agent must account for before editing. Nothing needed to call or reason about this read tool is missing.

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?

With a single parameter and 100% schema description coverage, the schema already documents projectId including its origin ('from video_project_create'). The description adds nothing about the input parameter, so the baseline 3 is appropriate.

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 (read) and resource (video project's timeline), then enumerates the returned content (main clips, B-roll, texts, captions, audio, revision, export price, editorUrl). This is detailed enough to distinguish it from the mutation siblings video_project_edit and video_project_create without opening their schemas.

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?

Gives a concrete trigger: 'Call it before editing and after a revision_conflict', with the rationale that the user may have changed the project in the editor. It does not name alternative tools or state when not to use it, but the pre-edit/conflict context is clear and actionable.

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