athena_gp_bma_decision_evsi

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 does convey that the operation is hypothetical and design-only, which signals non-destructive intent. However, it does not explain what the returned decision value looks like, whether any state changes are persisted, or what side effects might occur beyond the implied computation.

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 front-loads the core purpose ('Estimate decision value') and appends a useful design-only caveat. There is no wasted filler, and every phrase contributes something meaningful to the tool's identity.

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 tool has 8 parameters and no output schema, so the description must carry substantial contextual weight, but it remains only one sentence. It does not explain what 'decision value' means in this context, what outputs to expect, how actions/experiments relate to the EVSI computation, or how this tool fits alongside sibling EVSI/GP tools.

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 adds almost no parameter-level meaning. The phrase 'candidate GP measurements' loosely maps to the 'candidates' parameter, but required parameters like context_key, actions, and experiments, as well as cost_weight, risk_weight, samples, and seed, remain unexplained in both the schema and description.

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 ('Estimate decision value') and a clear resource ('candidate GP measurements'), and it explains the distinctive mechanism ('updating both finite-grid kernel weights and within-kernel posterior action means hypothetically'). This effectively distinguishes it from generic EVSI tools like athena_decision_evsi and even athena_gp_decision_evsi by highlighting the BMA and hypothetical update details.

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 provides no explicit guidance on when to use this tool versus alternatives such as athena_decision_evsi, athena_gp_decision_evsi, or athena_gp_bma_predict. The 'DESIGN_ONLY' note hints at a planning context but does not state usage conditions or exclusions.

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