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

With no annotations, the description does useful work by disclosing cost ($0.01, PRO tier) and the 500-item cap, plus the validation standard applied. It does not say what happens to failing pairs (partial response? per-item errors?), whether the call is read-only, or what the auth/subscription requirement entails beyond the schema's access_token field.

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?

One sentence, front-loaded with tier and price, then capability, then limit and rationale. No waste, though leading with price rather than the operation is a slightly awkward ordering.

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?

For a paid batch validation call with no output schema and no annotations, the description should say at least what comes back per pair and how invalid entries are handled. It covers cost, limit and ruleset but leaves the response contract unstated.

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 only 50%, but the description supplies the single most important constraint not encoded in the schema: the hard limit of 500 accounts per call. It doesn't further clarify pairing or formatting rules, which the nested schema already covers.

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 (Validate) and a precise resource (UK sort code + account number pairs), plus the rule set used (Vocalink/Pay.UK modulus). The 500-pair batch scope implicitly distinguishes it from the single-pair sibling sort_code_check.

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?

The parenthetical 'e.g. before a Bacs run or payee import' gives real usage context, but there is no explicit guidance on when to prefer this over sort_code_check or what to do with single lookups.

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