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

Annotations only say readOnlyHint=false and destructiveHint=false, which is thin. The description compensates richly: it discloses that the run bills the caller's own allowance, executes REAL tools including money steps if a mandate is granted, returns immediately with results landing as TRACES, and that the provider_id path adopts a copy first and heals stale adopted copies. No contradiction with annotations.

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 dense and front-loaded with the core action, then covers identification modes, billing, safety, and return behavior. It is longer than the typical description, but every sentence earns its place given the tool's complexity and risk profile. Slight deduction for the somewhat breathless formatting and the parenthetical about adopting a copy, which could be tightened.

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 tool with no output schema and thin annotations, the description covers everything an agent needs to call it correctly: what it does, how to identify the rig, what input means, billing consequences, safety warning about money steps, return behavior, and auth requirement. The only minor gap is that it doesn't describe the trace format, but it explicitly says results land as TRACES, which is enough for an agent to know where to look.

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 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining the semantic difference between the two identification modes: rig_id is for rigs you own/adopted, while provider_id+external_id is for published listings and triggers an adoption first. It also clarifies that input is whatever the rig declares. This is meaningful added value, though the schema already documents each 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?

The description opens with 'RUN a rig, for real, right now' and immediately distinguishes this from merely authoring, scheduling, or hooking a webhook. It names the exact resource (a saved rig) and the action (execute it on demand), and the contrast with sibling tools like rig_author and rig_stage_set makes the purpose unmistakable.

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 gives explicit when-to-use guidance: use it when you need to actually execute a rig rather than just create or schedule it. It also explains the two identification modes (rig_id vs provider_id + external_id), warns that running someone else's rig executes real tools and may move money, and tells the agent to read the rig first. This is far beyond a minimal usage note.

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