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

With only neutral annotation flags (readOnlyHint=false, destructiveHint=false), the description carries the full burden and excels. It discloses that non-live trigger types are 'saved as enabled:true and simply never fires', introduces the authoritative `trigger_wiring_status` field, and clarifies the anti-loop/anti-complexity rationale behind condition_expr limitations. It even acknowledges its own potential staleness, which is a high degree of transparency.

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?

The description is a dense single paragraph, but every sentence earns its place: it covers purpose, type inventories, live-status caveats, condition_expr syntax, a testing pointer, and tier restriction. It is front-loaded with the core action. Slightly less organized than a bulleted structure, but given the complexity, the length is justified and there is no fluff.

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 tool with a complex discriminated-union schema, the description covers all critical operational caveats: the non-wired triggers, the need to check trigger_wiring_status, the condition_expr limitation, the test_rule recommendation, and the tier gate. Since an output schema exists, the description wisely points to the returned rule's trigger_wiring_status field rather than explaining all return fields. No important context is missing for an agent to invoke this tool correctly.

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 baseline is 3, but the description adds meaningful value beyond the schema. It specifies the exact operators for condition_expr (gt/gte/lt/lte/eq), explicitly forbids AND/OR/loops, and highlights which trigger types are live versus not_yet_wired, which is critical for choosing among trigger variants. While the schema already documents each variant well, the description's high-level synthesis earns extra points.

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 description opens with a specific verb and resource: 'Persist a trigger -> action rule and register it with the evaluator.' It then enumerates the 7 trigger types and 6 action types, making the tool's scope unambiguous and clearly distinguishing it from sibling tools like create_signal and test_rule.

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 gives explicit when-to-use and when-not-to-use guidance. It warns that price_threshold and manual triggers have no live event source and 'simply never fires', and it explicitly directs the agent to 'Use test_rule immediately after creating to verify it fires as expected WITHOUT spending a real dispatch.' It also provides a tier restriction ('Tier: sp500+') and a fallback for complex conditions ('compose multiple rules').

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