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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower, and the description earns credit by adding real context: it is free to call, it performs an 'unsigned simulated sweep' (i.e., no signing, no on-chain state change), and it deliberately corrects a known pitfall — raw RPC overstates the collectible figure. That accuracy caveat is genuinely beyond the annotations.

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?

A single compact sentence with the cost signal front-loaded ('Free.') and zero filler. It is dense with domain shorthand ('per curve/escrow', 'raw RPC'), which skirts under-specification, but nothing is redundant.

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 four-field nested request at 0% description coverage, the description leaves an agent unsure what a 'collectible amount' result looks like, what units/denomination it returns, or what chain/platform values are acceptable. For a quote tool with no return documentation, this is materially incomplete.

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 0% — only the optional 'curve' field carries any description, while chain, wallet, and platform are undocumented. The description mentions 'per curve/escrow' but explains none of the four request fields, does not state whether curve is optional or how escrow is identified, and therefore fails to compensate for the coverage gap.

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 conveys that this computes a 'TRUE collectible amount' scoped to curve/escrow using a simulated sweep, so the resource is identifiable. However the verb is implicit ('quote' must be inferred), 'collectible amount' is domain jargon, and nothing distinguishes it from siblings like claim_worth_it, launch_economics, or agent_budget_guard. Purpose is guessable but not crisp.

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?

It contrasts itself with 'raw RPC' (which 'overstates reality') and flags itself as 'Free', but never tells the agent when to reach for this tool instead of the 21 sibling analysis tools. No prerequisites, no exclusion conditions, no named alternative tool.

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