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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds that the tool returns metadata (id, names, frequency) rather than actual data values, and that omitting `query` returns the full set of 143. It also clarifies that the query matches any language—behavioral details beyond the annotations.

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 three sentences: definition, return fields, usage. It is front-loaded with the purpose and includes a helpful example list, but the parenthetical list of indicator types and the Chinese name of DSEC are slightly verbose. Still, all sentences earn their place.

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 one-optional-parameter read-only tool, the description sufficiently explains the output fields (id, three-language names, frequency) and the filtering/list-all behavior. It also gives usage direction. Without an output schema, this covers what an agent needs to know, though pagination and sorting are not addressed.

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?

The input schema already describes `query` with 100% coverage. The description adds the essential behavior that omitting `query` lists all 143 indicators and that it matches names across English, Chinese, and Portuguese, which is not explicitly specified in the schema (schema only gives examples). This adds meaning beyond the structured 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 uses a specific verb ("Catalogue... Returns") with a clear resource: Macau's 143 official key statistical indicators from DSEC. It enumerates example indicator categories and explicitly names the downstream tool `macau_indicator`, distinguishing this catalogue tool from sibling data retrieval tools like macau_population or macau_gaming_revenue.

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?

It states the intended use: 'Use this to find the right id/name for macau_indicator.' It also provides example questions it answers ('what economic indicators does Macau publish', 'find Macau's tourism statistics'), which helps an agent decide when to call it. Though it doesn't list exclusions, the pointer to the sibling tool is explicit.

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