create_alert

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

With no annotations, the description carries the full burden and goes beyond a basic definition by disclosing the state machine (armed→triggered→cooldown→armed) and deduplication behavior (same data window not retriggered). It does not mention the pending order side effect, but that is already detailed in the order_spec parameter schema, so the description adds meaningful behavioral context without contradicting annotations.

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 two sentences, efficiently providing purpose, scope, condition reference, state machine, and dedup behavior. Every sentence carries substantive information with no redundant wording.

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?

Given the tool's complexity (8 parameters, nested objects, no output schema), the description covers core behavior and state transitions but omits what the tool returns and how the alert integrates with sibling tools like list_alerts or get_triggered_alerts. The side effect of creating a pending order is in the schema, but the overall lifecycle is incomplete without return value info.

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 description coverage is only 25%, so the description needs to compensate. It adds semantics for 'condition' (same AST as scan_market) and implicitly explains 'cooldown_seconds' via the state machine, but leaves other parameters like note, idempotency_key, and request_id unexplained. This is a partial compensation for the low coverage.

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 clearly states it defines a conditional alarm for a single symbol and timeframe, with a specific verb and resource. It distinguishes itself from create_composite_alert by explicitly limiting scope to a single symbol+timeframe, making the tool's purpose unambiguous.

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?

It provides clear context that the condition uses the same allowlisted filter AST as scan_market, giving the agent guidance on how to construct the condition. The single-symbol+timeframe scope implies when to use this tool over composite alerts, though it does not explicitly name alternatives or exclusion scenarios.

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