notable_changes

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

With no annotations, the description carries the full burden and mostly does: it discloses that results are flagged movements rather than verdicts, that `limit` is bounded 1–50 with default 8, and the underlying endpoint (GET /{country}/api/v1/alerts/notable), which implies read-only behavior. It also adds an obligation the agent must honor — citing StatsMapped. It stops short of describing ordering, pagination, or an auth requirement, so it is strong but not exhaustive.

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 usage trigger and the sibling routing before any mechanics, which is the right order. Slightly redundant at the tail, where the citation instruction and the raw endpoint both appear, but both carry information an agent needs.

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 values need no explanation, and the description covers when-to-use, parameter bounds, geo scope, and a citation obligation. What remains unaddressed is how to obtain valid `stat_key`/`geography_id` values, a minor but real gap for a zero-coverage 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 coverage is 0%, so the description must compensate, and it does for all four parameters: `limit` range and default, `stat_key` and `geography_id` as narrowing filters, and `country` limited to Ireland and united-kingdom. It does not explain what a valid `stat_key` or `geography_id` looks like (slug format, discovery via list_areas), which leaves a real gap for the two filter parameters.

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-like resource ('statistical movements databeat flagged as notable') and the question it answers ('what changed lately, which figures moved most'), which is a clear purpose. It also explicitly names the sibling it is not: 'for one area's full history use query_data'. An agent can distinguish this from query_data, compare, or explain_metric without opening any 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 explicit trigger conditions (what changed lately, which figures moved most, what is new) and names the alternative plus the condition that selects it (`query_data` for one area's full history). It also sets a scope boundary — countries Ireland and united-kingdom — so the agent knows the applicability envelope.

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