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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description's added value is elsewhere: it discloses the quota ('10 calls/day free'), the exact paid rate ($0.002/call), and the payment paths (x402 via params._meta, HTTP, or X-API-Key credits), plus the serving host. That is material operational context an agent cannot get from annotations or schema. It stops short of 5 because it says nothing about what happens on quota exhaustion (error shape, whether the call is billed when it fails).

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, front-loaded with the returned facts before the commercial terms. The pricing sentence is dense but every clause (free tier, per-call price, three payment mechanisms, host) carries distinct information. The host attribution is the only piece of questionable value.

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 an output schema present, return values need no prose, and the annotations cover the safety profile, so the description's remaining obligations are payment/auth and scope, both of which it handles. It is complete enough for an agent to call correctly, with the only gap being failure behavior at the rate limit.

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%, so the schema already defines chain, vault, and holder, and the chain enum is spelled out there. The description adds only marginal meaning by framing holder as 'a holder's position', implying it is optional and switches the response to per-holder data. Baseline 3 is appropriate given the schema does the heavy lifting.

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 names a specific resource (ERC-4626 vault) and enumerates the exact facts returned: underlying asset, total assets, share price, deposits open, and holder position. That is far more concrete than 'read vault data'. It does not differentiate itself from potentially overlapping siblings such as contract_read or dex_price, which keeps it from a 5.

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 only implied: an agent can infer it should call this when it needs vault state, and the mention of 'a holder's position' hints that supplying a holder changes the query. There is no explicit when-to-use, when-not-to-use, or named alternative among siblings.

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