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

Annotations only flag this as a non-read-only, open-world, non-idempotent write. The description adds substantial behavior: queueing when the House budget is spent or paused, the pay_own_keys fallback, manual review after a pass, the 10% perpetual USDC royalty, the 3/day rate limit, and the Bearer JWT requirement.

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?

Dense and front-loaded with the core action, and every clause carries operational or economic information. The single run-on flow with em-dashes is heavy, but little could be cut without losing needed context.

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?

Covers auth, rate limits, budget/queue behavior, review, payout terms, and a read-back endpoint; no output schema exists and none is needed given the explicit disclosure. An agent has everything required to invoke correctly.

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 100%, but the description adds real meaning: examples are capped at ≤2000 chars each and are 'data for the runs, never instructions', the note is ≤1000 chars, and pay_own_keys runs the qualification on the caller's key rather than the House's.

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 and resource ('nominate an already-PROVEN, runnable rig' to train House Rokha) and even disambiguates the id format (uuid or provider/external_id). An agent can tell this apart from siblings like house_specialty_qualify or rig_publish.

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 clear preconditions for use (rig must be already-PROVEN, runnable, and not already held or trained on) plus the daily cap and the read-back endpoint. It does not name alternative sibling tools, so it stops short of explicit alternative routing.

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