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

Goes well past the annotations (readOnly/openWorld/non-idempotent/non-destructive) by disclosing quota semantics ('one admitted API call consumes one shared account request, including admitted errors') and the absence of automatic retries, which directly explains why idempotentHint is false. It also constrains interpretation of the data ('preserve missing_dates; never interpolate') and pins the window to UTC.

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 kept to six short sentences with no filler. Some sentences are telegraphic fragments ('UTC window ends on to or today', 'No automatic retries') that read more like notes than prose, which slightly hurts scannability at the tail.

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?

An output schema exists, so return format need not be explained, and the description still covers the important non-schema context: UTC windowing, quota cost per call, no retries, and missing-date handling. It is thin on what 'approved stored variant' means and gives no hint about response size or limit behavior for larger windows.

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 67%: card_id and to are documented in the schema, while days has no description and no enum. The description adds meaning only for to, clarifying that the UTC window ends on that date or today, but says nothing about days or its 1-90 bound. Baseline 3 is appropriate given the schema carries most of the load.

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: read daily EUR observations for an approved stored variant, and adds the disambiguating scope note 'independently of its current price', which separates it conceptually from sibling price tools like get_card_prices and get_prices. It does not name any sibling explicitly, so an agent still has to infer the boundary from sibling names alone.

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?

'Use earlier to dates for older windows' gives one piece of operational guidance about a parameter, but there is no explicit statement of when to prefer this tool over get_prices, get_card_prices, or batch_prices. Usage is implied by the scope sentence rather than stated.

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