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

Goes well beyond the annotations: names the required X-JEV-API-KEY header, states that spend must be authorized, explains that deterministic vetoes short-circuit provider calls (cost behavior), and explicitly scopes the output as shadow research that never submits trades, signs payments, or uses an operator key. That is exactly the side-effect disclosure an agent needs for a non-readOnly, open-world tool.

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?

Four tight sentences, each doing distinct work: what it does, auth requirement, cost/veto behavior, and safety scope. Front-loaded with the action and no filler.

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?

No output schema exists, and the description does characterize the return as a shadow research review, plus covers auth, cost, and safety for a mutation-adjacent tool. Missing only detail on the evidence payload format and what a review contains.

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 coverage is 0%, so the description has to carry the load. It clarifies evidence (Cascade evidence) and model_spend_authorized (spend gate), but says nothing about instrument or observed_at semantics, nor the shape of evidence entries, leaving half the required parameters undocumented.

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?

States a specific verb and resource: run Jev jurors (by TypeSafe AI) over Cascade evidence, capped at five. It is clearly distinct from cascade_analyze/capsule/status by naming the jury mechanism, though it doesn't explicitly contrast itself with cascade_analyze.

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?

Gives one hard prerequisite (model_spend_authorized=true) and implies a BYOK key is needed, but never says when to reach for this over cascade_analyze or what evidence qualifies. Usage is implied rather than routed.

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