singapore_get_psi

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

Annotations already declare a safe, read-only, idempotent, open-world read, so the safety profile is covered. The description adds genuinely new behavior — default-to-latest semantics, local-limit scoping over 'timestamp groups', and an instruction to advance local offsets before reusing the preserved upstream pagination token. However, the last two sentences are jargon-heavy and an agent cannot confidently act on 'local limits apply to timestamp groups'.

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 purpose is front-loaded in one clean sentence and there is no filler. The two trailing sentences are compressed to the point of ambiguity, so they cost readability without delivering a clear instruction.

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 values need no explanation, and annotations cover the safety profile. Against that, this is a seven-parameter tool with almost no schema documentation, and the description leaves the most ambiguous selectors (area vs station_id vs region, and limit) undefined.

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 only 14% (just `date`), so the description carries most of the burden, yet it clarifies only the date/latest behavior and the offset/pagination_token relationship on a second read. Nothing explains `area`, `station_id`, or `limit`, including how station_id relates to region or that limit defaults to 20 with a max of 100.

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 opening clause names a specific resource (NEA PSI) plus the pollutants it covers and the regional breakdown, which is more precise than the bare tool name. It implicitly separates itself from the single-metric siblings (singapore_get_pm25, singapore_get_air_temperature) but never names one explicitly.

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?

Only 'latest if omitted' gives real usage context, telling the agent that no date means current readings. There is no statement about when to prefer this over singapore_get_pm25 or singapore_query_air_quality_annual, and no exclusions or prerequisites, so routing must be inferred.

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