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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds genuinely useful behavioral context beyond annotations: monthly update frequency, the 4–6 week publication lag, the source cube (snbmonagg), and the "no auth" requirement. This gives the agent realistic expectations about data freshness and access. No contradiction with annotations.

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?

Four sentences with zero wasted words: the resource is front-loaded in the first clause, units and cadence follow, then use case and provenance. The source/license sentence ("Source: Swiss National Bank data.snb.ch (cube: snbmonagg), Swiss OGD open license, no auth") packs trustworthiness and access information an agent needs. Every sentence earns its place.

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 read-only retrieval tool with two optional parameters, full schema coverage, and an output schema, this is complete. The description covers data source, update lag, units, license, auth requirements, and intended use cases. Nothing an agent needs to invoke this tool correctly is missing — the output structure is covered by the output schema, and the parameters are covered by the input schema.

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% — both limit and level_type are fully documented in the schema, including defaults and the default 24 for limit. The description's "Values in CHF millions (level) or percent period-over-period change" lightly reinforces the level_type semantics but adds nothing the schema doesn't already state. Baseline 3 is appropriate since the schema carries the parameter-documentation burden.

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 opens with a specific verb+resource: "Retrieve Swiss monetary aggregate statistics published by the Swiss National Bank," then enumerates the exact components (currency in circulation, sight deposits, M1, savings deposits, M2, time deposits, M3) with M1 labeled narrowest and M3 broadest. Units are pinned down (CHF millions or percent period-over-period change), and the title itself disambiguates from siblings like swissnbm.fx.rates and swissnbm.rates.policy. An agent can tell exactly what this tool returns 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?

The description provides clear use context: "Ideal for Swiss monetary conditions analysis, inflation research, and macroeconomic studies." This tells an agent when to reach for this tool. However, it stops short of naming specific alternatives or exclusions — it doesn't say "for FX rates use swissnbm.fx.rates" — so the agent must infer the boundary from the tool name. Clear context without explicit when-not/exclusions earns a 4.

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