memoire

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so effectively. It explains the tool's orchestration behavior, fallback mechanisms, success/error handling (including that individual step failures don't abort the plan), and return format. It also covers prerequisites and execution modes. The only minor gap is lack of explicit rate limit or performance characteristics.

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?

The description is well-structured with clear sections: purpose, prerequisites, return behavior, error handling, and examples. While comprehensive, it could be slightly more concise—some information about prerequisites and fallback mechanisms might be condensed. However, every sentence adds value, and the front-loaded purpose statement is strong.

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?

Given the tool's complexity (orchestrator with multi-step execution), no annotations, and no output schema, the description does an excellent job covering behavior, prerequisites, and examples. It explains the return format in detail despite lacking an output schema. The only minor gap is that without annotations, it doesn't explicitly state whether this is a read-only or mutating operation, though the examples imply both creation and audit capabilities.

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?

With 100% schema description coverage, the baseline is 3. The description adds value by providing context for the 'intent' parameter through multiple detailed examples that illustrate specificity requirements and domain concepts (atomic levels, component names). It also explains the practical use of 'dryRun' in the context of inspecting plans before execution, which complements the schema's technical description.

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 clearly states the tool's purpose: 'Run the agent orchestrator with a natural language design intent — classifies the task, builds a multi-step plan, and executes it.' It specifies the verb ('run'), resource ('agent orchestrator'), and distinguishes from siblings by focusing on orchestration of multi-step tasks rather than single operations like 'create_spec' or 'generate_code'.

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 description provides explicit guidance on when to use this tool vs alternatives. It states prerequisites (Figma connection requirements for design tasks), mentions it 'automatically dispatches to registered agent workers when available, or falls back to internal execution,' and includes intent examples that illustrate appropriate use cases. The 'Be specific' warning also helps distinguish from vague intents better handled elsewhere.

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