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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety profile is covered. The description still adds real value by disclosing determinism (SHA256) and zero model spend, and the 'admitted state' precondition hints at a gating requirement, but it never explains what admission requires or what fails without it.

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?

Two sentences, no filler, with the action front-loaded and the cost caveat trailing. It is tightly structured; the terseness is better counted against completeness than against conciseness.

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 tool with three undocumented required parameters and no output schema, the description should define what a Decision Capsule contains and what the caller must supply. It never describes the return value or the parameter expectations, leaving an agent unable to construct a correct call from the definition alone.

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?

All three required parameters (instrument, evidence, observed_at) have 0% schema description coverage, so the description carries the full burden and adds essentially nothing — no mention of instrument type, evidence shape, or timestamp semantics. The phrase 'from admitted Cascade state' is the only faint provenance hint.

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?

It pairs a specific verb (Build) with a named artifact (Decision Capsule) and a source (admitted Cascade state), but 'Decision Capsule' and 'admitted' are undefined jargon the agent cannot resolve without prior Cascade knowledge. Nothing in the sentence distinguishes it from cascade_analyze or cascade_review_jev, so purpose is only partially legible.

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 model spend' implicitly signals when to prefer this over a sibling that presumably incurs model cost, which is a usable but indirect selection cue. There is no explicit statement of when to use it, when not to, or which sibling it replaces, and no prerequisites are given for the 'admitted Cascade state' input.

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