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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely non-obvious context: data freshness ('Refreshes every 5 minutes') and the 0-100 risk-index scale with 24h delta, which an agent cannot derive from the empty schema.

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?

One front-loaded sentence that leads with the payload shape (risk index 0-100 + 24h change) and ends with the refresh cadence. The radar enumeration is long but each item conveys real scope, not filler.

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?

With no output schema, the description carries the return-value burden and does so by naming the metrics and the radar taxonomy. It stops short of describing the response envelope or keying (e.g. how radars are identified), which the sibling get_radar presumably resolves for detail views.

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?

The tool takes no parameters and additionalProperties is false, so there is nothing to disambiguate; baseline 4 applies. The description correctly implies a single unfiltered call returning all radars.

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?

A specific verb+resource ('get_radars') with an enumerated inventory of what each radar covers (geopolitics, politics, economy, crypto, energy, Open Web). The phrase 'every ... radar' implicitly distinguishes it from the singular sibling get_radar, but the distinction is never made explicit.

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?

Usage is only implied: an agent can infer this is the bulk/list view because it returns 'every' radar with a 0-100 index and 24h change. There is no explicit statement of when to call this versus get_radar, nor any note about when the index-level summary is preferable to detail.

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