get_metadata

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

The description calls this a "Get" and says nothing about side effects, yet the annotations declare readOnlyHint=false and idempotentHint=false with an openWorldHint — implying a non-read-only, non-idempotent operation. The large nested `implementation` block (skills, platform, systemUi, components) hints the tool also produces implementation guidance, a significant behavior the description never discloses.

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?

A single front-loaded sentence with no filler — structurally clean. The brevity is appropriate in form but leaves the substantive gaps noted elsewhere.

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?

For a 7-parameter tool with a nested object, no output schema, no schema descriptions, and no annotations explaining intent, one sentence is far too thin. The agent gets no idea what comes back (tree? provenance records?) or how the mutually exclusive input modes interact.

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 0% across 7 parameters, including a nested `implementation` object with six sub-fields and enums like platform/systemUi/components. The description never explains url vs fileKey+nodeId vs snapshotId, nor what depth and limit control, so it does nothing to compensate for the schema gap.

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?

"Get an outline and provenance" names a resource (Figma node or saved snapshot) but the operative terms are vague — it never says what an "outline" or "provenance" actually contains. It also does not distinguish itself from the closely related siblings get_design_context and figma_get_design_context, so an agent must guess which one to pick.

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?

There is no when-to-use guidance at all: no mention of which of the two input modes (node vs snapshot) to prefer, no prerequisites, and no reference to the many sibling tools such as get_design_context, get_screenshot, or figma_list_snapshots. The agent must infer selection from the name alone.

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