get_series

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

With no annotations, the description carries the full burden and does well: it discloses the authentication requirement (EVDS_API_KEY), hard range limits per frequency, the sampling semantics of weekly/monthly values (last bulletin of the period), and that observation values may be null. It stops short of describing error behavior or how out-of-range requests fail, which keeps it out of 5 territory.

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 payload, then progressively narrower constraints. Every clause carries information (key requirement, range caps, null caveat), though the long parenthetical on weekly/monthly bulletins is dense and could be tightened.

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-shape explanation is unnecessary; the description instead covers the operational facts an agent needs (auth, range limits, nullable observations). For a 6-parameter, dual-source tool this is close to complete, with only failure-mode behavior left 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 100%, so the baseline is 3, but the description adds real meaning beyond the schema: the series_code format distinction between EVDS and 'FX:<CUR>[:<rate_type>]' codes, the API-key split, and the range constraints that govern start/end choices. That is genuine added value over the field-level descriptions.

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 first sentence names the resource (time series) and enumerates what comes back: observations plus metadata (name, frequency, source) and citations. That distinguishes it from search_series (code lookup) and get_fx_rate (single rate), though the retrieval verb itself is only implied by the noun phrase rather than stated.

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 gives concrete conditions for the two code families: EVDS codes require EVDS_API_KEY, keyless FX codes work without one. The range caps by frequency (daily 62 days, weekly 1 year, monthly 5 years) tell the agent when a request is even valid, but there is no explicit 'use X instead when Y' routing against siblings like get_fx_rate.

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