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

With no annotations provided, the description carries the full burden. It discloses that the tool never persists, that the substrate verdict is returned without an observer, and that the crossed verdict appears only when an observer is supplied. This gives a good sense of side effects and output variability, though it does not detail error behavior or side-effect guarantees beyond persistence.

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 compact and information-dense, with no filler. It front-loads the core concept, then uses an em-dash list for the return components and a final sentence for usage context. The only minor issue is the slightly jargon-heavy opener 'Crossed-product audit explorer,' but it is followed by concrete clarification.

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 — seven parameters, nested objects, no output schema, and twenty siblings — the description covers the core purpose and return structure well. However, it leaves parameter semantics largely to inference, does not explain the relationship to compute_dealbreakers_v2 beyond 'same input,' and provides no detail about the structure of the verdict objects or the matrix rows. It is adequate but not fully complete for autonomous selection and 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 only 14%, so the description needed to compensate by explaining key parameters. It does add meaning for the observer object by listing the five archetype values and tying them to the output matrix, but it does not clarify stage, lensScores, stageProbabilities, or the optional boolean/integer fields. Most parameters remain underspecified from an agent's point of view.

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 crossed-product audit explorer that takes the same input as compute_dealbreakers_v2 and produces a substrate verdict, a crossed verdict, and a five-row archetype matrix. It distinguishes itself from compute_dealbreakers_v2 by explicitly naming that sibling and describing the additional archetype-oriented output.

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 states when to use the tool: for the dashboard 'view as [archetype]' dropdown and for previewing a verdict before committing. It also names compute_dealbreakers_v2 as the related alternative and explains how the observer parameter changes behavior. It lacks explicit 'do not use when...' exclusion criteria, but the context is clear enough.

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