figma_get_code_layers

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

With no annotations, the description carries the full burden and does so: it discloses that code layers are rendered-only, that a Desktop Bridge is required, and a non-obvious failure mode where links are omitted and 'linksUnavailable: true' appears unless the file window is focused. That conditional-result detail is exactly the kind of thing an agent could not infer elsewhere.

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-loaded with purpose, then limitations, then alternatives, then the focus caveat and the bridge requirement. Every sentence carries information, though the trailing 'Requires Desktop Bridge.' reads as appended rather than integrated and the block could be split for scanability.

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 3-parameter, no-output-schema read tool with no annotations, the description covers purpose, limits, prerequisites, and result fields. The remaining gap is pagination/limit semantics and what a result entry looks like beyond the field list, but nothing essential to calling it correctly 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 67% — scope and fileKey are already documented in the schema, and the description merely restates scope ('on the current page or across the file'). The limit parameter (default 100, max 500) is undocumented in both schema and description, so pagination behavior is left unexplained.

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?

Names a specific verb+resource and defines it precisely ('Figma's React code layers, node type CODE_INSTANCE'), then lists what it returns (position, size, page, dev resources/links) and the scope options. No sibling tool does this, and the description makes that distinction explicit by naming figma_capture_screenshot and send_code_to_figma as the adjacent tools.

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 the use case, explicit exclusions ('their source and props can't be read or edited, and new code layers can't be created through them'), and concrete alternatives for the excluded case (Figma UI, GitHub import, Figma's own MCP server send_code_to_figma). It also routes the agent onward to figma_capture_screenshot to visually inspect a found layer.

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