register_trigger

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'priority preemption and cooldown guards' which hints at some behavioral traits, but it does not specify side effects: does registering a trigger override an existing one? Does it require the target behavior to be loaded first? Is it idempotent? It doesn't mention any destructive or mutating actions, nor does it describe the response format. These gaps are significant for a tool with 9 parameters.

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 single sentence of about 12 words, concise and front-loaded with the main verb. It mentions key behavioral concepts ('priority preemption', 'cooldown guards') in a compact way. However, it uses abstract jargon that may require unpackingeding, and it doesn't include a second sentence to clarify the action enum or provide usage context É, which could make it denser but more helpful. Still, there's no waste — every word earns its place.

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 (9 params, 1 required, nested objects, no output schema, no annotations), the description is underwhelming. It doesn't explain the 'action' enum or that 'list' is an available operation, nor does it describe the return value (nothing to tell the agent what to expect). It doesn't cover request prerequisites (e.g., does the behavior need to exist?) or error conditions. The nested 'condition_params' object is entirely unexplained. With so many parameters and no annotations, the description is far from complete for correct invocation.

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 0%, so the description must compensate for undocumented parameters. While the description doesn't explain individual parameters (e.g., what 'condition_params' does), it highlights two key concepts: 'priority preemption' (maps to the 'priority' parameter) and 'cooldown guards' (maps to 'cooldown_ms'). This adds semantic meaning beyond the bare schema. However, it doesn't cover other parameters like 'trigger_id', 'behavior_name', or 'condition_type', which are left to inference. But given the coverage is 0%, the description does provide some value. With 9 params, a score of 4 is reasonable because it at least characterizes the most central parameters, even if it omits many others.

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 states a specific verb ('Configure and manage') and resource ('reactive interrupt triggers'), but the phrase is somewhat abstract — it doesn't specify exact actions like 'register' or 'list' that the schema reveals. It differentiates from siblings only partially: it mentions triggers but doesn't clearly distinguish from 'manage_behaviors' or 'load_behavior'. The term 'reactive interrupt triggers' is jargon-heavy and assumes the reader knows the domain, making it less clear for a general agent.

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 offers no guidance on when to use this tool vs. alternatives. It doesn't mention that the 'action' parameter selects between 'register' and 'list', nor does it provide context about when registering a trigger is appropriate vs. using other tools like 'manage_behaviors' or 'set_parameters'. There are no exclusions or explicit 'when not to use' statements. The agent must infer usage entirely from the schema and sibling names.

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