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

With no annotations supplied, the description carries the full load and does well: it discloses the paid model ($0.05 USDC per call via x402 in _meta["x402/payment"]), the free sample=true escape hatch capped at 3 rows, and data provenance (World Bank series codes, OpenAlex ROR ids). It also states a privacy posture ('Facts only; no personal data'). It does not cover failure modes, rate limits, or freshness beyond 'latest measured', which keeps it from a 5.

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?

The paragraph is dense but front-loads the core value, then routes, then pricing and the free-preview hint — a sensible ordering with no filler sentences. The opening question is slightly expendable and the long parenthetical indicator list makes it a heavy single block, but every clause carries 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?

There is no output schema, so the description must convey return content, and it does: each indicator comes with its measurement year and World Bank series code, and institution records carry ROR ids. Combined with the route/parameter mapping and pricing disclosure, an agent has enough to invoke correctly. It lacks return-shape detail (field names, ranking order, empty-result behavior) for a multi-route tool.

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 real meaning by binding each route to its parameters: /rank takes indicator, since, limit; /answer takes country; /compare takes countries. It also explains the purpose of sample (free 3-row preview) beyond the schema's terse 'Free preview, max 3 rows'. It could go further by giving format examples for indicator codes or country codes.

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?

After an opening rhetorical question, the description states concretely what the tool returns: measured education indicators for 209 countries (literacy, enrolment, completion, spending, pupil-teacher ratio, out-of-school children, R&D, researchers, gender parity) plus OpenAlex institution counts with ROR ids. That is a specific resource with enumerated content. It stops short of 5 because it never names how it differs from plausible siblings such as country-economy or science, leaving the agent to infer the boundary.

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 usage modes: compare up to 6 countries, or rank all countries on one indicator, and maps each to a route (/rank, /answer, /compare, /coverage) with required parameters marked by asterisks. What is missing is when NOT to use it — no pointer to country-economy or science for overlapping data, and no guidance on picking between /rank and /compare beyond the cardinality hint.

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