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

With no annotations provided, the description carries the full burden of behavioral disclosure. It openly states that the three sources are independent, that specialisation RSCA is trade-based and unrelated to PRODCOM production figures, that lists are pre-sorted and should be used as-is, and that prodcom_code is passed through untouched with ambiguity left to the caller. It does not mention authorization, rate limits, or failure modes, but for a combinational read helper, the behavioral caveats and composition logic are well disclosed.

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?

Though the description is long, it is densely packed with essential information: purpose, alternatives, independence warning, data handling quirks, and return shape. Every sentence contributes new value, and the structure is logical (what it combines, how to interpret, what to do with ambiguous mappings, what it returns). The length is justified by the complexity of the behavior.

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?

The tool is complex (combines three independent sources with caveats), but the description covers the composition, the key behavioral warnings, the prodcom pass-through policy, and the return envelope. An output schema is present, so the description does not need to detail every return field, yet it still mentions the main parts (narrative_facts, chart_data, available, reason). For a contextual aggregation helper, this is complete.

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 baseline is 3. The description adds meaningful semantics beyond the schema by explaining that prodcom_code is passed through untouched and that ambiguous mappings are never guessed here, and by specifying how the query object is shared across endpoints. It also clarifies that the top-8-by-value breakdown appears as chart_data, which gives extra context to the n_top and output structure. This exceeds the baseline.

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 identifies the tool as a report-section helper that combines three named data sources (get_specialisation, get_concentration, get_production_series) into a unified 'Market structure' output. It distinguishes itself from siblings by explicitly naming the underlying tools and explaining how they are bundled, making the purpose unambiguous and differentiating it from alternatives like get_market_summary or get_overview.

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 explicitly states when to use this tool (as a 'Report-section helper' for the 'Market structure' section) and names the alternative tools it aggregates, even noting they are independent and should be treated as separate findings. It also gives specific guidance on prodcom_code handling, telling the caller to resolve ambiguities rather than having the tool guess. This is strong usage guidance.

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