Get annotations

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds genuinely useful behavior beyond that: an empty result is 'a normal answer, not an error', the editor support matrix, and the presence of a `scope` field naming the root that was read.

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?

Three sentences with no waste: the resource and its payload lead, the empty-result expectation follows, and the environment note closes. Every sentence earns its place and the most decision-relevant fact is front-loaded.

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 usefully sketches the return shape (per-annotation category/label/colour, dev resources, a `scope` root name), so an agent can interpret results. It stops short of covering failure modes other than empty results or behavior on very large subtrees.

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 nodeId's defaulting chain (selected layer, then current page) and the session/file-selection logic are already documented in the schema. The description adds no parameter-level detail, which is the correct baseline when the schema does the heavy lifting.

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?

The description names a specific resource (annotations on a node or subtree), defines what annotations are ('the notes designers leave for developers'), and adds the dev-resources payload in the same breath. It never mentions a sibling such as figma_get_metadata or figma_get_design_context, so an agent must still guess which read tool to reach for when several return node data.

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?

The line 'Editors: Design; unverified: FigJam, Slides' functions as an environment constraint on when this call is reliable, and the empty-result note heads off a common false failure. However, there is no guidance on when to prefer this over sibling read tools (metadata, design context, node info), and no prerequisites for the session parameter.

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