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

Annotations already declare a read-only, idempotent, non-destructive, closed-world analysis, and the description adds real behavioral context beyond that: `ok` is false when a finding is high or the spec does not check (then `refusals`), findings carry stable R- ids and a severity, and the tradeoff section explains what a cheater gets at each trust level. It does not describe runtime cost, limits, or latency, and the 'file' input path it mentions has no counterpart in the schema, which weakens an otherwise strong disclosure.

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?

Purpose and the sibling exclusion are front-loaded in the first clause, and the output enumeration mirrors the actual return shape, which matters given there is no output schema. But the prose is a dense run-on chain of clauses with repeated framing ('what a cheater gets' appears three times) and prescriptive instructions that blur description with workflow, so it is longer and harder to scan than it needs to be.

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 and a nested free-form `spec` object, the description carries the full burden of describing the return value, and it does so field by field (ok, refusals, routes with kind/trust/ceiling/feeds, findings, tradeoffs), which is exactly what an agent needs to consume the result. The one gap is the phantom 'file' input path that the schema does not support.

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 100% for the two parameters, so the baseline is 3, and the description mostly restates them. It adds one useful precedence hint, but it also says the spec can be given as 'a file' while the input schema has only `spec` and `example` with additionalProperties: false, so the extra guidance is partly misleading rather than additive.

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 ('Review an economy') plus the angle ('the way a cheater reads it, before it goes live') and immediately differentiates from the nearest sibling with 'not a validity check: xsolana_check is that'. An agent can tell what it produces (routes, findings, tradeoffs) without opening any other tool.

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?

Explicitly names the alternative (xsolana_check) and the condition that selects it, ties use to a pre-launch moment, and points at xsolana_examples for valid `example` names. It also states what to do with the output ('Fix every high finding, declare "trust" honestly ... tell the person in plain words'), leaving no ambiguity about when this tool is the right call.

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