predict_bayesian

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

Annotations already provide safety profile (readOnly, destructive, idempotent, openWorld). Description adds behavioral context: how prior is seeded (Beta(prior*10, (1-prior)*10)), that it produces a calibration score, and is free. No contradictions.

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?

Four sentences: purpose, explanation, use cases, alternatives. No unnecessary words, front-loaded with action verb, 'Free.' appended. Every sentence earns its place.

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 moderate complexity, presence of output schema (not needing return value doc), and complete annotations, the description fully covers purpose, parameters, usage context, and alternatives. No gaps identified.

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 has 100% description coverage, so baseline 3. Description adds the Beta prior seeding formula and clarifies evidence format (value in [0,1], weight). This provides meaning beyond schema definitions.

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?

Description clearly states the tool updates a prior probability with weighted evidence using Beta-Bayesian posterior, specifies exact use cases (fraud-risk scoring, A/B test stopping, diagnostic probability stacking), and distinguishes from siblings predict_ensemble and simulate_montecarlo.

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?

Explicitly states when to use (incremental belief revision) and when not to: for combining independent model predictions use predict_ensemble, for full distribution sampling use simulate_montecarlo.

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