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

Annotations only declare write/idempotent/non-destructive; the description adds the real behavioral facts: the state-gate (rules outside the expected state are left untouched), the return value (count of updated rules), and the required 'write' scope. This is exactly the context an agent needs before mutating state.

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 short sentences, front-loaded with the action and starting state, then the sibling alternative, then the partial-failure semantics and return value. No filler.

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 single-parameter mutation with no output schema, the description covers the precondition, the effect on Kord's follow-ups, the non-matching-rule behavior, the return value, and the auth scope. Nothing an agent needs to call it safely is missing.

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 is already documented as pattern_id UUIDs with a pointer to ficiel_list_learned_patterns. The description adds no further meaning about the parameter (e.g. batch limits or ordering), so the baseline 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 (active/adopte) and resource (règles apprises proposées par Kord), plus the starting state 'proposed'. The sibling it is not — ficiel_dismiss_learned_patterns — is named directly, so an agent can distinguish the two without opening a schema.

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?

Names the alternative (dismiss) and its effect, and gives a precondition: only rules in the expected 'proposed' state are touched, others are skipped. That is close to explicit when/when-not guidance, though it never states a positive trigger scenario beyond the implied 'a rule is proposed'.

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