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

With no annotations, the description carries the full burden; it does disclose that the tool is purely advisory (no side effects) and deterministic against engine state ("Same policy as the reference client"). It also implies polling semantics via defer/wait. It omits any statement on auth/idempotency and never says what the response object looks like, which matters since there is no output schema.

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 entire definition is one ~130-word sentence with five levels of nested parentheticals and pipe-delimited clauses, e.g. the "list" branch nests three alternatives inside a condition. Content is information-dense, but structure is a parsing obstacle; a short bulleted branch list would serve the agent far better.

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 multi-branch policy tool with no annotations and no output schema, the description does cover all six outcome branches and their preconditions, which is the essential content. It stops short on two fronts: undefined terms (grace_s, solver election by rank, least-claimed-then-cheapest) and no indication of the shape of the returned move beyond the enumeration.

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?

Single required parameter with 100% schema description coverage ("Your registered agent_id"), so the schema already does the work. The description adds nothing about agent_id semantics; per the high-coverage baseline this is a 3.

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?

"ONE advisory move from engine-verified state" does state a specific verb/resource and enumerates the six possible outcomes, so the agent knows it gets a single recommendation. However, heavy undefined jargon ("elected broker", "grace", "viable coalition", "engine-verified state") obscures what the recommendation actually means, and no sibling tool is named to anchor the mapping (bounty_combine, bounty_solve, bounty_advertise).

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 extensively specifies branch conditions for each move (combine only if you are the elected broker, defer if another is broker, wait if nothing you solve helps), which is strong in-domain when-to guidance. But it never states the tool-level usage rule: whether to call this before acting, and that the returned move should then be executed via the corresponding sibling tool. That routing is left to inference.

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