athena_contingent_policy

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

With no annotations provided, the description carries the full burden. 'DESIGN_ONLY' usefully signals that the tool does not execute the policy, but the description does not state whether the design is persisted, what is returned, or whether the belief state is modified. Key side-effect questions remain unanswered.

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 a single, front-loaded sentence with a clear imperative and a terse, high-signal qualifier 'DESIGN_ONLY.' Every word adds meaning, and it avoids redundant restatement of the input schema.

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?

With three required parameters, nested objects, no output schema, and no annotations, the tool needs a richer description. It states the core purpose but omits return format, parameter structures, side-effect expectations, and guidance for the actions array. It is not complete enough for reliable invocation.

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% and no parameter descriptions are present. The phrase 'one supplied experiment' maps to the experiment parameter, and 'current finite belief' hints at context_key, but the actions array and exact meaning of context_key are left unexplained. The description only partially compensates for the undocumented schema.

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 uses a specific verb 'Build' and names the exact artifact: 'depth-1 outcome-contingent action policy.' It adds scoping conditions ('under the current finite belief and one supplied experiment') and distinguishes itself from execution-oriented or multi-stage policy tools via 'DESIGN_ONLY.'

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 clear invocation context: depth-1, current finite belief, one supplied experiment, and design-only mode. It does not explicitly name alternatives or state when not to use the tool, but 'DESIGN_ONLY' and 'depth-1' imply boundaries versus execution or multistage planning tools.

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