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

Annotations only declare a safe read, but the description discloses far more: a 5,000-point cap with truncation semantics, paging via from/to, how gaps and gap_notes are reported, that projections are kept out of points unless include_projections is passed, and the full as_of vintage model (vintages, revised_later, vintage_coverage_starts, not_on_record). This is exactly the kind of behavior an agent cannot infer from readOnly/idempotent hints.

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 and nearly every sentence carries distinct information (limits, gaps, projections, transform, as_of). It is long, but for a 12-parameter tool with no output schema the return-shape enumeration and feature notes are load-bearing rather than padding.

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?

Given a complex tool with 12 parameters and no output schema, the description covers the return envelope (indicator, place, frequency, points, total_points, truncated, gaps, source, other_frequencies, projections) plus the paging, projection and as_of behaviors an agent must know to call it correctly. Nothing material is left to guesswork.

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 and the schema already documents each parameter. The description goes beyond per-parameter docs by explaining cross-parameter interaction ('transform works as in get_value, on every point', window usage, transform.inputs/gaps, transform not combinable with include_projections, no projections under as_of) and giving concrete example payloads.

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 opening sentence states a precise verb+resource+scope: 'Get the time series of an indicator for one place, oldest to newest, from one source so the points are comparable.' The 'one place, one source, oldest to newest' framing lets an agent distinguish this from a single-value lookup, though it never names the sibling get_value explicitly, so it stops just short of full sibling differentiation.

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 trigger contexts ('Use it for trends: evolution of the CPI by month, population of Mataró since 2015') and states combination rules ('Not combinable with include_projections', projections never returned with as_of, pass from/to to page). It does not spell out when to prefer get_value or compare instead, so alternatives remain implicit.

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