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

Annotations already declare readOnly/non-destructive, so the bar is lower, and the description adds real value: it calls out that the call is project-scoped and ignores the active-project pointer, that it renders only the windows around each device, and that it emits per-device metrics. It omits cost/latency context for a render-bound operation, which is the main remaining gap.

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-loads the two most important facts (project scope, READ) before detailing outputs, and each sentence carries operational content. Slightly dense with metric jargon and a trailing imperative that could be tightened, but no filler.

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 burden of describing returns and does so concretely (frame strip, onion, seven named metrics). Safety profile is covered by annotations. The unresolved start/end semantics and absent render-cost expectation are the only notable omissions.

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 low at 25%, so the description must compensate. It explains ids thoroughly (fx or motion ids plus the last-write default) but says nothing about start or end, which are presumably the frame range bounding the rendered windows. Half the parameters 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 ('prove devices on rendered frames') and enumerates precisely what it produces: a 10-frame strip from -3 to +6, an onion of changed pixels, and named metrics. This lets an agent distinguish it from generic render/inspect siblings like render_preview without opening the schema, though the term 'prove' is niche jargon that the description has to unpack.

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 supplies a useful default for ids ('the devices changed by the last write') and a follow-up instruction ('Remove or move anything that does not land'), which implies its role as a verification step. However, it never says when to prefer this over look_at or render_preview, nor any precondition beyond the project scope.

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