singapore_query_schools

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered. The description adds real context beyond that — bundled-catalog source coverage and the advice to fetch metadata for current coverage — which is useful freshness disclosure. It says nothing about result shape, but an output schema exists, so the omission costs little.

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?

Four tight sentences, front-loaded with the resource and the dataset id an agent needs first. 'Topic: education' is filler, and the coverage sentence is slightly cryptic, but overall there is very little waste.

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 filtered-read tool with an output schema and full annotation coverage, this covers purpose, query mechanics, prerequisite discovery step and data-freshness caveat. The only soft spot is that a reader must infer the filter/field vocabulary from a separate inspection call.

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?

All six parameters are named by capability: exact filters, column text search (q), fields, sort, pagination (limit/offset). Schema coverage is 50%, and the schema already supplies examples for q, sort and filters, so the description largely restates. The genuinely additive piece is the pointer to inspect the dataset to discover valid field names.

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 (Query) and resource (General information of schools, Ministry of Education), and pins down the exact dataset id d_688b934f82c1059ed0a6993d2a829089. Among ~50 dataset-specific siblings, the resource name makes it unambiguous which dataset this targets, though it does not explicitly contrast itself with the generic singapore_query_dataset.

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 an explicit prerequisite: inspect dataset d_688b... first to learn the filter fields. That is actionable sequencing an agent should not have to infer. It offers no explicit when-not or sibling alternative, but the siblings are distinct datasets, so the guidance gap is minor.

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