singapore_search_catalog

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

Goes beyond the readOnly/idempotent annotations by disclosing that results carry a snapshot date, that the catalog is a static bundle, and that non-tabular hits may need a download before querying — real workflow consequences. It stops short of saying how results are ordered or what pagination behavior to expect across limit/offset.

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 short sentences, front-loaded with the capability and its offline scope, then the workflow and the staleness caveat. No filler and every clause carries operational information.

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?

The output schema and readOnly annotations cover return shape and safety, and the description handles the workflow well. But for a nine-parameter search tool, the absence of any guidance on filtering semantics (status, coverage_year, updated_since) leaves a meaningful gap for an agent trying to narrow results.

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 0%, so the description must carry parameter meaning, yet it only glosses query (English keywords), agency, and format. The six remaining parameters — limit, offset, status, coverage_year, updated_since, include_unknown_coverage — get no explanation of expected values or semantics anywhere.

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 (search), a specific resource (the bundled full data.gov.sg catalog), and the axes it searches on (English keywords, agency, format). The 'bundled'/'no network needed' framing plus the named follow-on tools separates it cleanly from sibling entry points like list_catalog_page and lookup_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?

Explicitly routes the agent forward: inspect_dataset then query_dataset, download for non-tabular data, and list_catalog_page when the snapshot is stale. It gives both the when-to-use and the when-to-use-something-else conditions rather than leaving the workflow to inference.

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