Set the brief of new work

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

Beyond annotations, the description discloses where state lands (a brief block at an empty spot, on nodeId, or merged via briefId), that force bypasses a STALE refusal ('read it again and resend'), and includes idempotencyKey retry semantics. Together with the strict-mode gating and sign-off interaction, this is rich behavioral context that annotations alone don't convey.

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?

Nearly all sentences carry real information, and the action is front-loaded, but the body is a dense run-on that crams roles, storage, update modes, and strict-mode gating into one block. It would read better split into purpose, storage, and strict-mode sentences.

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 35-parameter, nested, role-dependent tool with no output schema, the description is largely complete: it covers the required fields, role taxonomy, storage/update paths, and strict-mode behavior. Minor gaps remain around what the call returns and how block drawing interacts with layout, but the core call is well supported.

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 already 91%, so the baseline is 3; the description still adds meaning by mapping each role to the skill it reads first (ux→screens/flows, presentation→slides, board→figjam, motion→storyboard) and by characterizing `details` as the role's own keys. It exceeds the schema baseline without duplicating every field.

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?

Opens with a concrete verb+resource: 'Record the brief of new work before its first frame.' It enumerates the brief's fields (role, gear, title, goal, message, success), the roles with their skills, and the storage targets (brief block, nodeId, briefId). An agent can tell this apart from figma_get_brief and the creation 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 concrete timing ('before its first frame') and states that under BRIDGE_PROCESS=strict certain creations 'wait for a brief, and figma_sign_off ends it,' which clearly frames when the tool is required. It doesn't explicitly compare against a non-brief flow or state exclusions, so it's clear context rather than full when/when-not guidance.

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