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

Annotations already declare readOnly, idempotent, non-destructive, open-world, but the description adds useful context they do not carry: the data source/provenance (University of Southampton) and 'Keyless' (no auth required). It also states the return is a summed count. It does not mention latency or async behavior in the description itself, though the schema covers that.

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 in the first sentence, with the input/output contract and differentiation following. Every sentence carries information, though the 'AUTHORITATIVE' aside and trailing 'Keyless.' fragment make it slightly dense. No 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 correctly states the return ('the summed population count back'). Input geometry, CRS, year range, and the keyless/no-auth fact are all conveyed, and the schema covers async polling. Adequate for a single-operation compute tool, though it could note error behavior for malformed or unclosed rings.

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 description coverage is 100%, so all four parameters (year, dataset, geojson, runasync) are already documented with types, defaults, ranges, and format hints. The description restates the GeoJSON/WGS84 input and the year range but adds no syntax or semantics beyond the schema, so the baseline of 3 is appropriate.

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 ('total population inside any polygon'), names the data source and resolution ('WorldPop 100 m gridded population estimates'), and bounds the input ('GeoJSON Polygon or MultiPolygon in WGS84'). This is clearly distinguishable from siblings worldpop_datasets (list datasets) and worldpop_task_status (job status).

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 concrete when-to-use framing: 'AUTHORITATIVE for "how many people live inside this boundary" at arbitrary geometry' with named scenarios (catchment, flood extent, service area, proposed district), plus the contrast against census tables that only cover official units. It stops short of explicitly naming an alternative sibling to use instead, so it falls just short of a 5.

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