Layers on the current page

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false). The description adds genuine behavioral context beyond that: it discloses that the operation walks the layer tree from the page down, that depth is the mechanism, and that a deep page yields thousands of rows — a scale warning an agent needs before calling. It stops short of describing the return structure, so it doesn't reach 5.

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 with zero waste. The core purpose is front-loaded first, and the depth caveat plus sibling routing come second. Every clause earns its place; no redundancy with the schema or 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?

Complete enough for a single-parameter, read-only navigation tool. The only gap is that the return format of the layers (node IDs, names, types) isn't described, and there's no output schema to fill that in. But for walking a layer tree, the missing structure detail is minor against a strong purpose, usage, and scale warning.

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 100% and the depth parameter is already well documented ('How many levels to walk. Default 1.'). The description adds minor value by contextually framing depth as walking down and tying it to the row-volume trade-off, but the schema already does most of the work, 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 and resource ('The top-level layers of the page the designer is looking at') with a clear scope tied to the current page. Explicitly names the sibling it is not — 'prefer figma_get_children on one branch' — so an agent can distinguish it from the closest alternative without opening either schema.

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 an explicit alternative (figma_get_children) and the condition that selects it (walking down one branch vs. the whole page). Also warns about the cost of increasing depth ('a deep page is thousands of rows'), which directly informs the agent's decision to stay shallow or switch tools.

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