aetre_correlated_posterior_update

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool calculates a posterior and prevents overconfidence, which are beneficial outcomes, but does not disclose whether the operation is read-only, any side effects, or specific requirements beyond the API key mention. The 'Enterprise license key required' phrase is somewhat contradicted by the schema (api_key is not in required list), but this is a schema-description mismatch, not an annotation contradiction. No further behavioral detail is given.

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, focused sentence that leads with the primary action and purpose. It avoids redundant phrasing and front-loads the key concept. It is concise without being under-specified, though it could include a bit more usage context without becoming verbose.

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?

The description covers the core purpose and mentions the key differentiator (correlated noise) but lacks guidance on the expected output format (e.g., does it return a tuple of mean and variance?) and does not specify any prerequisites besides the API key. Given there is no output schema, the description should at least hint at the return shape. It also does not provide usage scenarios or caveats. For a complex Bayesian tool, more detail would be helpful.

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?

The schema has 100% description coverage, so all parameters already have descriptions. The tool description adds contextual meaning (correlation, overconfidence) but does not deepen the meaning of individual parameters like prior_mean or prior_variance beyond what the schema already states. For example, it does not explain how inter_agent_correlation is used in the calculation beyond what the schema already says. Baseline 3 is appropriate given the high schema coverage.

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 a specific action ('Calculates') on a specific resource ('Bayesian posterior mean and uncertainty'), with a distinctive qualifier ('under correlated multi-agent evaluator noise'). It also mentions the purpose ('preventing artificial overconfidence from redundant LLM outputs'), which differentiates it from sibling tools focused on queues, VOI, staking, etc. The verb and resource are unambiguous.

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 the tool (when you need posterior updates with correlated noise) but does not explicitly state when not to use it or point to any alternative sibling. It does not mention conditions like 'use aetre_calculate_voi for value of information' or any exclusion criteria. The guidance is only implicit through the problem statement.

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