record_fact

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

With no annotations, the description carries the burden and does useful work: it signals a write operation and explains state-transition behavior—facts start as provisional, are upgraded by evidence, and supersedes_id chains replacements. It does not mention permissions or side effects beyond creation, but the core lifecycle is clearly disclosed.

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?

Three tight sentences put the primary action first and then add only high-value context: the grounding requirement, the provisional lifecycle, and the supersede behavior. There is no filler or restatement of schema fields.

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 write tool with 8 parameters and no annotations or output schema, the description covers the critical source and replacement logic but omits the meaning of domain, confidence, symbol_id, and artifact_id, and says nothing about return values. It is sufficient for the common path but not fully complete.

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 coverage is only 25%, and the description adds meaning for source_observation_id, source, and supersedes_id by explaining their roles. However, required parameters content and domain, plus confidence, symbol_id, and artifact_id, are left to inference, so the description only partially compensates for the low 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 phrase 'Record a grounded FACT' names a specific verb and object, and the capitalized FACT plus 'grounded' distinguishes it from sibling record_belief. The requirement to cite a source observation or raw source string further pins down what this tool does and what it does not.

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?

It gives a clear precondition: source_observation_id must come from a prior cpg_think promote, or a raw source string must be supplied. It also explains the facts lifecycle, but it does not explicitly name record_belief or state when not to record a fact, so it stops short of a full when/when-not contrast.

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