build_brain__build_product

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

With no annotations, the description carries the full behavioral burden. It does add real value by declaring capability limits (no network, filesystem, shell, or secrets) and the isolated-no-net sandbox, which tells the agent this is a self-contained generation step. It stops short of explaining how the finished product is returned when no filesystem is available, or whether the operation is long-running or resumable.

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 core sentence is tight and front-loaded, but it is wrapped in tag-like metadata ('[Warden PROVISIONAL A/99 ✓]', pinned sha256) that consumes attention without helping invocation. Those tokens could be moved out of the description body.

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 no-output-schema tool that produces a whole 'shippable product', the agent still doesn't know the return shape — single document, multiple files, bundle, or summary — nor where the artifact goes given the no-filesystem constraint. The sandbox and capability notes are useful, but the deliverable contract 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?

The single 'task' parameter is fully documented in the schema with an example, so semantics are already covered. The description adds a little meaning by framing the input as a 'validated idea' rather than an arbitrary prompt, which qualifies what belongs in 'task'.

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 gives a specific verb and outcome: turn a validated idea into a complete, verified, shippable digital product. The schema example ('a budgeting workbook for freelancers') clarifies the deliverable is a content artifact, not code. It does not distinguish the tool from siblings such as build_brain__ship_gate, which sounds like part of the same pipeline.

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?

'Turn a validated idea into...' implies a precondition that upstream validation (e.g. research_brain__idea_scout or fact_gate) should happen first, but this is never stated explicitly. There is no when-not guidance and no naming of the sibling that handles the shipping/gating step.

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