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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: what the response contains (verified date, official source URL, applicable period, signature), how max_age flips status to 'stale', how nextExpectedChange interacts with status, and how ambiguous keys degrade to a candidate list. That is exactly the kind of behavioral detail annotations cannot carry.

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?

Front-loaded with the core purpose and the key-format convention, with the more specialized behaviors (max_age, nextExpectedChange, status, batching, coverage) following in order. It is one dense paragraph and the seven inline key examples make it run long, but every clause carries information an agent needs.

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?

There is no output schema, so the description must carry the return shape — and it does, listing verified date, source URL, period, signature, status and nextExpectedChange. It stops short of describing the full response envelope for batches or what an unknown key returns besides candidate keys, which keeps it at 4 rather than 5.

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%, so the baseline is 3, but the description goes further by explaining the consequence of max_age (the answer is marked `stale` when verification predates the bar) and the batch semantics of comma-separated keys. It adds outcome-level meaning rather than restating the schema's syntax.

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 ('the current value of one official figure by key') and enumerates the concrete fact types (threshold, rate, allowance, fee, deadline, limit, policy rate). It does not name or contrast the sibling tools resolve_fact or what_changed_since, so differentiation is left to 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?

Rich operational guidance is present — key format with five worked examples, loose-key resolution with candidate fallback, comma-separated batch up to the schema's limit, and per-key max_age. However, it never states when to use this instead of resolve_fact or what_changed_since; the relationship to resolve_fact is only hinted at via the loose-key resolution sentence.

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