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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds genuinely new behavioral context: the call acts only on the explicit project_id, never guesses from the active-project pointer, and echoes that project identity with the result. It does not reconcile the odd idempotentHint=false on an ostensibly read-only tool, which is the one unexplained trait.

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 sentences, both front-loaded with the operative label (PROJECT-SCOPED, READ) before the detail. It is dense and purposeful rather than padded, with no restatement of the title.

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 carries the return-value burden and does so reasonably: rendered frames with anchors, and the project identity returned alongside. It omits frame format, resolution, or how many frames come back, which an agent might want for a visual inspection call.

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 20% (project_id alone is documented). The description partially compensates by clarifying the core distinction between frames at source times versus output_times of the edit, but start, end, and times remain undocumented in both places.

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 and resource (read frames with measured anchors drawn: face mesh, hands, pose, tracks/objects/planes) and scopes it with the PROJECT-SCOPED prefix. It clearly reads the 'world' layer rather than raw media, which implicitly separates it from siblings like look_at and look_at_asset, though it never names those siblings.

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 clear context for invocation: verify a hand is up, an object's outline, or a quad before and after a world write. It does not name alternative inspection tools (look_at, look_at_asset) or state when this is the wrong choice, so it stops short of full routing guidance.

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