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

Annotations already cover read-only, idempotent, non-destructive, closed-world, so the safety profile is free. The description adds useful behavioral context the annotations lack: the payload contains screens in canvas order with images and viewer text, and runId flags changed screens — both relevant to response size and use.

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 short sentences, no waste, with the caller/purpose front-loaded and the alternative second. Everything earns its place.

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 an output schema present and 100% parameter coverage, the description needn't explain return values, and it adds the key fact that this is viewer-facing. Nothing essential is missing, though a note on whether direct agent invocation is supported would close the last gap.

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 100%, so all three parameters including runId and locale are already documented in the schema. The description adds no parameter-level meaning beyond that, which is the baseline-3 case when the schema does the work.

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 ('load a project's screens ... in canvas order, with their images and the viewer's text') and identifies its caller, so an agent knows exactly what this does. It also names the sibling it is not (list_components) for the self-read case.

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?

'Called by Sleek's screen viewer' establishes this is the viewer's loader, and 'To read screens yourself, use list_components' routes the agent to the alternative. The one gap is that it never explicitly says the agent should not call this directly, though the implication is strong.

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