check_invariant

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

Describes return format (list of violations with file/line) and implies read-only nature, though could explicitly state non-destructive behavior. No annotations exist, so description carries the burden.

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?

Concise with front-loaded purpose, clear differentiation, use cases, and return info. Every sentence adds value.

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?

Comprehensive for a check tool: explains purpose, when to use vs alternatives, return format, and includes examples. No output schema but return description suffices.

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 covers all 4 parameters, but description adds value by providing a Datalog rule example and explaining the rule's role beyond schema.

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?

Clearly states the tool checks one-off invariants using Datalog rules and returns violations. Distinct from siblings like create_guarantee by specifying ad-hoc vs permanent use.

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 says use for ad-hoc checks and points to create_guarantee + check_guarantees for persistent rules. Provides concrete use cases with examples.

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