athena_cycle_advance

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

Despite lacking annotations, the description discloses key behavioral traits: it advances through real internal phases, stops at typed WAITING_* states, and does not simulate. This goes beyond a generic 'advance' and informs the agent of the tool's limits. However, it does not mention return value, error handling, or the exact meaning of 'CYCLE.1', leaving some gaps.

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?

Two sentences, front-loaded with the action verb. No filler or redundancy; every phrase (e.g., 'real internal phases', 'WAITING_* state') adds meaning.

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 no annotations, the description covers the core operation but omits important context: the effect of max_steps, what the tool returns, and prerequisites or error conditions. It also uses the cryptic 'CYCLE.1' without explanation, making it incomplete for a complex stateful operation.

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 description coverage is 0%, so the description must carry parameter meaning. It maps 'inputs' to 'newly supplied witnessed inputs' but leaves cycle_id implicit via 'CYCLE.1' and says nothing about max_steps. With 3 parameters, only one is partially explained, so the compensation is inadequate.

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 advances a cycle (verb+resource) and specifies it merges newly supplied witnessed inputs. The phrase 'through as many real internal phases as possible' and the stopping condition distinguish it from cycle_start and cycle_state.

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?

It implies when to use it: when you have new witnessed inputs to merge and want to advance a cycle as far as possible. It also explicitly states it does NOT simulate measurements, execution, or tests, providing a clear when-not. While it does not name sibling alternatives, the context is sufficient.

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