list_rules

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

No annotations are supplied, so the description carries the burden. It does disclose meaningful behavior beyond the schema: results mix machine-derived and human-adopted rules, and adopted rules carry violation counts and examples from the current run. It does not state ordering, pagination, whether derived rules also carry counts, or error behavior for an unknown saved_as.

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?

A single dense sentence with no filler, and the important distinction (code-found vs human-adopted) is front-loaded. The parenthetical examples of rule kinds earn their space by making the resource concrete.

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 one-parameter read tool with no output schema, the description covers what the returned entries are and where the violation data comes from, which is the core need. Gaps remain around result ordering, whether every rule category gets counts, and failure modes for an invalid saved_as.

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 100% and the single parameter saved_as is already described as the run's save name, sourced from list_runs or build_ontology. The description adds nothing about the parameter, so the baseline of 3 applies.

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?

States a specific verb (list) plus resource (rules) and distinguishes two categories the tool returns: rules discovered by code in the data (giving concrete examples like a field with values on every object, or two dates always ordered) and rules adopted by humans. An agent can tell this is a read of rule definitions, unlike the mutating sibling set_rules, though no sibling is named explicitly.

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?

Usage is only implied: the agent infers it is the way to inspect rules for a saved run, and that set_rules is the counterpart for changing them. There is no explicit 'use this when...', no prerequisite statement, and no note on what to do if saved_as is unknown.

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