athena_belief_register

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

With no annotations, the description must carry full weight but only mentions 'register/reset' and 'normalized priors.' It does not disclose side effects, whether existing state is overwritten, permissions, error behavior, or return values. The note about non-canonical truth is abstract, not operational.

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 concise and front-loaded, but overly terse. It wastes no words, yet the second sentence ('Model belief is not canonical truth') is a philosophical caveat that may be less valuable than explaining key aspects of the tool.

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 3 parameters and no output schema, this description is incomplete. It lacks critical details about what 'models' contains, how 'context_key' scopes the state, what 'replace' does, and what success/failure responses look like. The provided context is minimal.

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 the description does not explain 'context_key', 'models', or 'replace'. The word 'reset' hints at the replace boolean but is far from explicit, leaving the agent to infer parameter meaning from names alone.

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 is specific with a clear verb ('register/reset') and resource ('finite discrete model belief state'), and adds detail about normalized priors. It distinguishes from the sibling tool athena_gaussian_belief_register by specifying 'finite discrete' vs. Gaussian.

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 usage for finite discrete models, contrasting with Gaussian belief tools, but does not explicitly mention alternatives or provide when-not-to-use guidance. The caveat about non-canonical truth hints at epistemic context but lacks clear selection criteria.

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