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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, and the description goes well beyond them: it discloses the response shape (verified date, source URL, applicable period, signature), the `stale` flagging behavior driven by max_age, batch semantics, candidate-key fallback on ambiguity, and the coverage boundary. That is substantive behavioral context not present in the structured fields.

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?

Purpose is front-loaded, then key format, then modifiers, then coverage — a sensible order with no wasted framing. It is dense and example-heavy (seven worked keys, including a deep path), which is mildly redundant but defensible for demonstrating the key grammar; a little trimming would tighten it further.

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 four parameters, no output schema, and no enum guidance, the description carries the load well by describing return contents, staleness behavior, and multi-key batching. The one loose thread is the closing '`coverage` lists the rest', which references something not exposed as a parameter and is ambiguous without further context.

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 schema already documents all four parameters; the baseline would be 3. The description still adds meaning the schema lacks — that comma-separated keys produce a batch return, and that max_age marks the answer `stale` rather than filtering or erroring — which is genuine semantic value beyond the field definitions.

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 (get) and an exhaustively enumerated resource — 'one official figure by key — a tax threshold, rate, allowance, fee, deadline, limit or policy rate' — plus what comes back with it. An agent can tell this is a single-key fact lookup rather than a search or history tool without opening the schema.

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 explains batch usage (comma-separated keys) and the ambiguity/degradation path ('a loose key is resolved when unambiguous; otherwise the answer lists candidate keys'), which implies when a resolve step is needed but never routes to the resolve_fact sibling explicitly. No statement of when to prefer this over resolve_fact or what_changed_since, and no exclusions.

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