athena_belief_observe

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

No annotations are provided, so the description must carry the full transparency burden. It states a Bayesian update occurs but does not disclose whether the update mutates the belief in-place or returns a new belief, nor does it mention side effects, storage behavior, or requirements like prior existence of the belief context. The description is terse and leaves the tool's operational behavior largely opaque.

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, well-structured sentence that places the action verb first and includes the essential qualifiers ('finite,' 'explicit per-model,' 'one actual declared'). It contains no redundant or irrelevant information, earning a high score for conciseness.

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?

Given the tool's complexity (5 parameters, nested object, no output schema), the description is too sparse. It does not explain how to construct the likelihoods object, the meaning of context_key in relation to a belief, or what the tool returns. The omission of these details leaves an agent without enough guidance to correctly invoke the tool in a real workflow.

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 compensate. It maps 'likelihoods' to 'explicit per-model likelihoods' and 'outcome' to 'actual declared observation,' but it does not explain the structure or format of the likelihoods object, the role of context_key, or the purpose of optional parameters like actor and evidence_ref. Several parameters remain semantically unexplained, making correct invocation difficult.

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 ('Bayes-update') and names a specific resource ('finite belief') while clearly differentiating the operation from sibling tools by requiring 'explicit per-model likelihoods' and 'one actual declared observation.' This distinguishes it from similar belief or observe tools, providing clear purpose.

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 implies when to use this tool: when you have explicit per-model likelihoods for a finite belief and a single observation. It does not explicitly name alternative tools or exclusions, but the 'explicit per-model likelihoods' and 'finite belief' phrasing gives clear context. However, no direct contrast with sibling tools is provided.

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