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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the agent knows this is a safe, repeatable read that does not contradict the purchase-decision framing. The description adds useful behavior context by naming the decision payload, the four evidence kinds and the offer shape, plus the constraint that verdicts come from registry-run benchmarks only. It says nothing about latency, rate limits, or the human-approval requirement that governs any resulting purchase.

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 purpose is front-loaded in the first clause, which is good, but the second half is a dense run-on enumeration of return fields ('decision, expected effect, price, confidence, reasons, operator_message, next steps and an ak.offer.v1 offer (...)'), which is hard to parse and competes with the actionable call guidance in the final sentence.

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?

With no output schema, the description must carry return-value disclosure, and it does list the top-level fields and the offer structure. However, it gives no indication of the shape or format of those values, and for an 8-parameter tool with nested objects it omits prerequisites such as the standing human-approval rule that determines whether a positive verdict can actually be acted on.

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 high (88%), so the baseline would be 3, but the description adds real meaning by telling the agent that model, expected_runs and baseline_cost_estimate_usd together produce a money estimate and that savings are reported only for measured models. This makes those optional parameters actionable rather than incidental. The nested constraints and budget_policy objects get no narrative treatment beyond what the schema provides.

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 (decide/evaluate) and resource (a registry capability) with the decision framing made explicit: 'whether a registry capability is worth buying for your task'. It also scopes the evidence source ('from registry-run benchmarks only'). It does not, however, differentiate itself from close siblings like compare_capabilities or estimate_roi, which an agent must choose between.

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?

Usage is implied rather than stated: the 'worth buying for your task' framing implies a pre-purchase decision, and 'from registry-run benchmarks only' implicitly excludes other evidence. There is no explicit when-to-use vs when-to-use-an-alternative guidance despite four sibling tools covering adjacent decisions (compare_capabilities, estimate_roi, get_quote).

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