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

Goes beyond the annotations meaningfully: it discloses that SHELL replays riders on every start ordered heaviest-first, and that a newer decision on the same scope retires the older one — a real side effect not covered by destructiveHint=false. The 'never put secrets in a rule' caution is also useful operational guidance. It does not say what the response looks like or how duplicates behave, which is why it is not a 5.

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?

Dense but front-loaded: purpose first, then behavior, then per-kind requirements, then a safety caveat. A few domain terms ('SHELL', 'mot catalog') assume context, but nearly every sentence carries distinct information.

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 non-idempotent write with no output schema, the description covers side effects (retirement of older decisions), ordering behavior, and a security caveat. Remaining gaps — return value and duplicate handling — are minor given the annotations already declare it is non-destructive and non-idempotent.

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%, so the schema already documents all six parameters including kinds, weight range, and decision-only fields. The description reinforces the decision triple (scope, said_at, quote) and the scope-collision rule, adding a little meaning beyond the schema, but nothing about value formats that the schema does not already carry.

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 and resource ('Add a rule ... for this line') and enumerates the rule kinds it accepts, so an agent knows exactly what is being created. It does not explicitly contrast with line_rider_list or line_rider_retire, so sibling differentiation is only implicit through the verb and kind list.

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 implies when to use it (when the owner has a brand/naming/tone/forbidden/language/decision/proof rule to persist) and gives conditional requirements for decisions. It never states when not to use it, nor points at line_rider_retire for removal or line_rider_list for inspection, leaving the alternative routing to the agent.

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