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

Annotations already supply readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description goes beyond these by disclosing the critical behavioral nuance that figures are 3-MONTH MOVING AVERAGES, explaining that '2026-06' means April–June, and noting the keyless/`source` character of the data. This is valuable behavioral context annotations cannot convey.

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 description is dense but efficient — roughly three sentences covering purpose, example queries, data source, and the moving-average caveat, all front-loaded with the core purpose. Every sentence earns its place, and the use of CAPS emphasis ('ONE call', '3-MONTH MOVING AVERAGES', 'PREFER') draws attention to the most important distinctions.

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?

Given a single optional parameter, no output schema, and rich annotations, the description covers everything an agent needs: what data is returned, the interpretation caveat (moving averages), the source, and the boundary against a sibling tool. There is no ambiguity left about invocation or result interpretation.

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 single `months` parameter is fully documented in the schema (range 1-120, default 12). The description adds a modest but useful note that 'The headline fields always describe the newest', which clarifies the relationship between the series and the main headline outputs. This complements, rather than repeats, the schema definition.

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 description states a specific verb+resource ('Hong Kong's headline labour-market figures in ONE call') and enumerates exactly which metrics are returned (unemployment rate SA and NSA, underemployment, labour-force participation). It also names the data source (Census & Statistics Department table 210-06101), distinguishing it clearly from sibling tools like censtatd_get_table and censtatd_table_info.

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?

The description provides explicit when-to-use triggers with natural-language examples ('PREFER for "what is Hong Kong's unemployment rate"', 'HK jobless rate') and provides an explicit alternative: 'Use censtatd_get_table for anything deeper (by age, sex, industry)'. This clearly delineates this tool's scope from a deep-dive sibling.

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