compute_dealbreakers_v2

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

With no annotations, the description carries the full behavioral burden and mostly delivers. It discloses non-obvious decision logic: GO requires three simultaneous conditions, KILL triggers on ≥2 blockers or score<50, and the KILL gate is observer-invariant ('fatal stays fatal'). It also explains the observer-triggered crossed-product pipeline. It does not describe output format or side effects, but the core verdict semantics are transparent.

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 dense sentence, but every clause contributes thresholds, pipeline details, or an invariant behavior. It front-loads the methodology and key verdict rules before explaining the observer pathway. While dense, the complexity of the tool justifies the compressed structure.

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 complex 7-parameter tool with nested objects, no output schema, and no annotations, the description covers the main GO/KILL logic and observer pipeline well. However, it omits the return-value shape and the meaning of several optional inputs such as sector, stageProbabilities, and contradiction flags. It is sufficient for invoking with required parameters but incomplete for full understanding of all inputs and outputs.

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 14%, so the description must compensate for the missing parameter documentation. It adds meaning to stage, lensScores, confidence, and observer, but it does not clarify sector, stageProbabilities, hasMajorContradiction, or unresolvedContradictions. The term 'blockers' is used without mapping it to a schema field, leaving several inputs semantically opaque.

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 identifies the tool as a Methodology v2 dealbreaker computation, specifying the GO conditions (score≥80, zero red flags, avg confidence≥0.6) and a KILL gate. It conveys an algorithm centered on stage-aware weights and confidence-weighted lens scoring, which is specific enough to distinguish it from generic compute siblings. However, it does not explicitly name the return object or call out how it differs from closely related tools like derive_kill_criteria.

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?

There is no explicit guidance on when to choose this tool over alternatives such as compute_crossed_matrix or derive_kill_criteria. The only usage hint is the conditional observer behavior: when observer is omitted, only the substrate verdict is returned. No exclusions, prerequisites, or alternate-tool routing are provided, so the agent must infer selection indirectly.

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