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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond that: the 200-month cap is refused rather than silently truncated, missing months are ABSENT rather than zero, and the credit class (comex, up to 2 tools per 60-second session = 1 credit) is disclosed. It doesn't detail pagination or exact response shape, but the output schema exists and the description covers the non-obvious behaviors that would surprise an agent.

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 every sentence earns its place: the return shape, the date semantics, the cap behavior, the absence-vs-zero semantics, the filter combination, the sibling routing, and the credit cost. It is front-loaded with the core purpose and scoping constraints before the sibling differentiation and credit note. No filler or repetition of schema content.

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 read-only, idempotent list tool with a 100%-covered schema and an output schema present, the description is complete. It covers the default window, the cap, the missing-month semantics, how filters combine, how to resolve entity references, which sibling handles related questions, and the credit cost. An agent has everything needed to select and invoke the tool correctly without opening the schema.

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 description coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema: it explains that `from`/`to` are YYYYMM and default to the last 24 published months, that `codes` and `countryIds` can combine to draw a single product-and-partner line, and that the span cap is enforced by refusal. It also cross-references kyrodata_resolve_entity for codes and countryIds, which the schema mentions but the description reinforces. This is meaningful added value over the schema, though not exhaustive.

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: 'Returns Brazil's monthly export or import series as rows' and immediately specifies the row structure (month, value USD FOB, volume kg, implied price per kg). It distinguishes itself from siblings by naming kyrodata_compare_trade and kyrodata_list_trade_partners as the tools for different question shapes, so an agent can tell them apart without opening schemas.

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 ('This hands over the POINTS') and when not to: 'A question about them — two equal windows compared — is kyrodata_compare_trade, and a ranking of partners inside one window is kyrodata_list_trade_partners.' It also gives concrete behavioral constraints: default window, 200-month cap, refusal rather than truncation, and absence-vs-zero semantics. This is explicit when/when-not guidance with named alternatives.

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