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

With no annotations, the description carries the whole burden and does so: it discloses the paid model ($0.1 USDC per call via x402 with _meta["x402/payment"]), the free sample=true 3-row preview escape hatch, the monthly rebuild cadence, and that facts are sourced with attribution. Those are exactly the cost and freshness facts an agent needs before spending money on a call.

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?

It is front-loaded with the core question and then dense but almost entirely factual: coverage, data sources, price, preview, refresh rate, routes. Every clause carries information, though the single paragraph-packing of routes and pricing makes it slightly harder to scan than a split structure would be.

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 nested-object, multi-route, paywalled tool, the description covers scope, data provenance, freshness, cost, free preview, and the return artifact (a ready-to-paste Markdown page). With no output schema present, it still tells the agent what comes back, leaving nothing essential 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 route-to-parameter mapping (city + country for /answer, q for /search, limit for /countries) that the schema's generic route and params descriptions do not spell out. The example "/HND" in the schema does not match any listed route, which muddies the picture slightly but is a schema artifact rather than a description 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?

The opening question plus "One-city dossier" states the verb/resource concretely, and the body enumerates the exact payload (population and rank, GHSL built-up population 2000/2025, OSM road/rail/park shares, elevation, airport/seaport, NOAA climate normals, 5 insights, a Markdown page). That is far more specific than sibling names like world-cities or place-brief, so an agent can separate them without opening schemas.

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 clear context on when this fits: any of 6,902 cities over 100k people, and it names the three routes with their required parameters (/answer city*, /search q*, /countries limit), which directs invocation. It never names an alternative tool or an explicit "use X instead" exclusion, so it stops short of full when-not guidance.

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