record_belief

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

No annotations are provided, so the description carries the burden. It discloses a key side effect: when belief_kind='assumption', it also creates a linked ASSUMPTION control-plane node. It also states the requirement to cite supporting FACT/OBSERVATION ids. It doesn't mention whether the operation is reversible or what the return value is, but the disclosed side effect is significant and useful.

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?

Two sentences with no filler. The first sentence states the purpose and the key requirement; the second adds the conditional side effect. Every word 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?

For a tool with 8 parameters and no output schema, the description covers the essential behavioral context: what counts as a belief, the evidence requirement, and the assumption side effect. It doesn't explain the remaining parameters (domain, risk_id, expiry_condition, verification_target) or return behavior, but the core decision an agent needs—when to call this vs record_fact and what to provide—is present.

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 only 13%, so the description must compensate. It adds meaning by explaining the purpose of supporting_ids (backing evidence) and the special behavior of belief_kind='assumption'. It also clarifies that supporting_ids is required for belief and hypothesis but may be omitted for assumptions, which is not fully clear from the schema alone. It doesn't explain domain, risk_id, expiry_condition, or verification_target, but the core semantics are covered.

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 the tool records an uncertain BELIEF (inference, hypothesis, assumption) and distinguishes it from sibling record_fact by emphasizing uncertainty and the need to cite supporting FACT/OBSERVATION ids. It also names the specific belief_kind values and the special behavior for 'assumption'.

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 gives clear context: use this for uncertain beliefs, must cite supporting FACT/OBSERVATION ids, and notes the special case for assumption. It doesn't explicitly say 'use record_fact for certain facts' or list exclusions, but the contrast with record_fact is implicit and the required supporting_ids guidance is strong.

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