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

readOnlyHint already declares this a safe read, so the description's job is to add context — and it does: it discloses the 1,000-identifier ceiling, guarantees output order matches input order, and states that unknown identifiers are silently omitted rather than causing an error. That omission behavior is exactly the kind of surprise an agent needs warned about; it only stops short of describing failure modes for malformed or cross-chain input.

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 front-loaded sentence with the batch cap and ordering guarantee stated before the edge-case omission rule. No preamble, no restatement of the tool name, nothing that could be cut without losing information.

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, the description needn't document return values, and annotations cover the safety profile; the remaining essentials — batch cap, ordering, omission semantics — are all covered. The one gap is sibling disambiguation against get_token and list_tokens, which an agent must resolve from tool names 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?

Schema coverage is 100% for the single 'tokens' parameter, so the baseline is 3, but the description earns extra credit by supplying a constraint absent from the schema — the 1,000-entry maximum (the schema sets only minItems: 1, no maxItems). It also reinforces cross-chain acceptance, consistent with the array-of-{chain_id, address} shape.

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 verb and resource ('Fetch canonical metadata for ... token identifiers') and qualifies it as a batch operation with a hard cap of 1,000. The word 'batch' implicitly separates it from the single-token sibling get_token, but no sibling is named explicitly, so differentiation requires inference.

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 1,000-item batch framing suggests this is for resolving many tokens at once, while get_token and list_tokens would be alternatives. There is no explicit 'use this instead of X when Y' routing, and no note on what to do when some identifiers resolve and others do not.

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