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 concrete context beyond annotations by stating the data source ('sdmx.ilo.org') and that no auth is required. It also notes the dimensions returned. It doesn't contradict annotations, and it enriches the behavioral profile without repeating annotation info.

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 moderately concise, packs essential information (purpose, example, usage, data source, auth) and uses a dash to separate the purpose from additional notes. It's front-loaded with the core action, and every sentence earns its place. Slightly longer than ideal but not bloated.

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 the output schema exists, the description doesn't need to detail returns, but it still explains what dimensions are returned (reference area, frequency, measure, sex, age) and that code lists are provided. It covers where to get the dataflow id, the purpose, and auth requirements. Nothing an agent needs to invoke it correctly is missing.

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% and both parameters are described, so the baseline is 3. The description adds value by providing a concrete example for dataflow_id and explaining how to use it to get dimensions and build key filters. It also clarifies that version is optional ('Omit to use the latest version') in the schema, which the description reinforces by implying it.

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 opens with a specific verb and resource ('Get the dimensions and valid codes for an ILOSTAT dataflow') and provides a concrete example ('DF_EMP_TEMP_SEX_AGE_NB'). It implicitly distinguishes itself from sibling tools by stating it returns dimension code lists, which contrasts with ilostat.dataflows (which lists dataflows) and ilostat.series.data (which fetches data).

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 states when to use: 'Use this to interpret the dimension labels returned by ilostat.data, or to build a narrower key filter' and points to the sibling source for the required id ('dataflow_id from ilostat.dataflows'). This gives clear context and routes the agent to the correct workflow.

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