get_segment_counts

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

With no annotations, the description carries the full burden and excels. It discloses the default geo (EU27 + NO + CH), the optional year, the effect of exclude_micro, the return structure (per-code plus segment_total), and a critical CAUTION about potential double-counting and the need for de-duplication. These are substantial behavioral traits beyond what the input schema reveals.

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 well-structured with a summary, labeled Args, Returns, and a CAUTION. Every sentence contributes essential information, with no filler. The example for nace_codes and the caution are valuable additions without excessive length.

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 tool with 4 parameters and no annotations, the description is highly complete. It covers all parameters, return structure, default behavior, and a critical data-quality caveat. An output schema exists, so the description does not need to detail every field, but it still gives a high-level summary of per-code and segment_total results. The sibling context is implicitly addressed through the geo parameter reference and the segment-specific focus.

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 has 0% description coverage, so the description must compensate fully. It does: nace_codes is explained with an example, geo references get_enterprise_counts and states the default, year specifies 'single year string, or omit for latest,' and exclude_micro is described as excluding micro firms (0-9) from the SME bucket. Every parameter gains meaning not present in the schema.

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 clearly states a specific action: 'Enterprise counts for a list of NACE codes that make up one value-chain segment, returned per code AND summed for the whole segment.' This identifies both the resource (NACE-coded segment) and the unique aggregation behavior (per-code and total sum), distinguishing it from siblings like get_enterprise_counts and get_company_count. The reference to the 'Company Counts by Segment' sheet further anchors its specific use case.

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 gives clear context by stating it maps directly to a row in a specific sheet, implying when to use it. It also provides a caution about double-counting and references get_enterprise_counts for the geo parameter, signaling a related alternative. However, it does not explicitly say 'use this instead of get_enterprise_counts when you need segment totals,' so it stops short of the explicit alternatives required for a 5.

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