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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior. The description adds real behavioral context beyond them: a hard cap of at most 400 points per call, the period-end convention for aggregated rates, and a mandatory citation/attribution obligation.

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 purpose, then constraints, then the citation requirement. Dense and largely waste-free, though the verbatim citation string is heavy and could be delegated to the result's cite field instruction more compactly.

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 4-parameter read tool with no output schema, the description covers the important behavioral facts: point cap, aggregation semantics, and citation duty. Remaining gap is what happens at the 400-point boundary (truncation vs error) and default date range.

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 50% (start/end documented as YYYY-MM-DD; id and frequency bare). The description usefully explains that frequency aggregates to W/M/Q/Y averages with period-end for rates, but adds nothing for id or start/end, so it only partially compensates for the coverage gap.

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 ('History of one series') and immediately disambiguates from the sibling by noting the id comes from search_series. An agent can distinguish this from search_series/search_releases without opening a 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?

Gives clear context: use it for one series, with an optional aggregation choice, and points to search_series as the source of the id. It lacks explicit when-not-to-use guidance (e.g. how to get more than 400 points, or when to prefer get_table).

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