singapore_query_lta

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context — an LTA_ACCOUNT_KEY credential requirement and the fact that some filters/offsets are silently inapplicable — but says nothing about rate limits, error behavior, or what happens when an unsupported filter is passed.

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?

Three short sentences with no filler, and the credential requirement is placed early. The telegraphic noun-phrase opening ("LTA lists and alerts") is slightly under-specified rather than merely concise, but the overall size is appropriate.

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?

An output schema exists, so return-value explanation is not required. Still, for a 5-parameter multi-dataset tool with 0% schema coverage, an agent is left guessing which of the 13 datasets accept service_no/bus_stop_code and which support offset — information the description gestures at but never resolves.

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 0%, so the description must carry the load. It does explain that service_no and bus_stop_code are endpoint-dependent and that offset requires a paginated dataset, which is real added meaning. But it leaves the 13-value dataset enum, limit bounds/defaults, and which specific datasets are paginated entirely undocumented.

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 phrase "LTA lists and alerts" identifies the resource domain (Land Transport Authority datasets) but supplies no verb or object specificity — it never says it queries/retrieves LTA dataset records. Combined with the dataset enum an agent can infer the purpose, but it cannot distinguish this tool from siblings like singapore_query_dataset or singapore_get_bus_arrivals based on the description alone.

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?

"Stop/service filters are allowed only on provider endpoints supporting them" and "Offsets apply only to paginated datasets" give conditional guidance about when filters work, which implies usage. However, there is no routing guidance relative to the many sibling query tools (e.g. singapore_query_dataset, singapore_get_bus_arrivals), and no statement of when not to use this tool.

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