Search nodes by name or type

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

Annotations already establish readOnly/destructive/openWorld safety, so the bar is lower. The description adds genuinely useful behavior: the result's `scope` echoes which root was searched, pagination is via limit+cursor, and cell hits name their `cell` and variant hits name the variant shown.

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 core purpose and stays dense without filler; each clause maps to a real capability. The parenthetical enumerations are heavy but all load-bearing, so it is efficient rather than bloated.

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 10-parameter search tool with no output schema, the description covers match modes, scope semantics, pagination, the session/file-selection concern implicitly, and routes to the right sibling. Nothing essential is missing.

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% (baseline 3), but the description adds meaning beyond the schema: `text` is defined to span TEXT characters, sticky/shape/connector labels, code blocks and table cells, and componentId resolves a variant set to every variant's instances.

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 (find/search) and resource (nodes) and enumerates the three match modes (name substring, text content, node type) plus the componentId instance-lookup mode. It clearly separates itself from siblings like figma_scan_nodes_by_types and figma_scan_text_nodes.

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?

Explains when each match mode applies and names the alternative for the full-text case ('Every text in a subtree: figma_scan_text_nodes'). It stops short of stating when to prefer this over figma_scan_nodes_by_types or the *_info getters, so no explicit when-not guidance.

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