erinys_collide

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

With no annotations, the description carries the full burden of disclosing behavior, but it does not state whether the collision mutates state, persists data, requires a session, or has side effects. 'Generate insight' is vague about what the tool actually does or returns.

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, front-loaded sentence with no filler or repetition. Every word contributes to conveying the action and purpose.

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?

The presence of an output schema covers return values, and the two simple parameters are self-explanatory. However, the description lacks usage context, behavioral transparency, and any relationship to sibling tools, making it minimally viable but not complete.

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?

The description mentions 'two observations', conceptually mapping to obs_a_id and obs_b_id, but it does not explicitly name the parameters or explain ID requirements. Since schema description coverage is 0%, more detail would help, but the parameter names are self-explanatory.

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 uses a specific verb 'collide' paired with a clear target ('two observations') and an intended outcome ('generate insight'). It is distinct from sibling tools by naming a unique action, though 'collide' remains metaphorical and does not explicitly differentiate from tools like link or traverse.

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?

No guidance is given for when to use this tool versus alternatives such as erinys_link, erinys_traverse, or erinys_conflict_check. The word 'Manually' hints at user-initiated use but does not provide context, prerequisites, or exclusions.

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