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

Annotations already establish read-only, idempotent, closed-world behavior, but the description adds materially more: the deals-module dependency that makes deal fields read zero/empty as a module gap rather than a real absence, the output-cap truncation of the index with countries_served and next_offset disclosure, and the licence attribution obligation on indicator and dataset entries. These are exactly the operational traps an agent would otherwise fall into.

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?

It is front-loaded with the domain and the two-mode split, and every clause carries information. The pagination sentence is dense and repetitive (next_offset named, then offset serving from that country named again in countries_offset), which costs a little readability in an otherwise efficient single paragraph.

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?

There is no output schema, so the description must carry the return contract itself, and it does: it enumerates what the index returns, what the single-country record returns including gap disclosures, how truncation surfaces, and what attribution fields must be preserved downstream. Nothing an agent needs to call the tool twice and interpret the results 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 already well documented in the schema, so the baseline is 3. The description adds an ISO 3166-1 alpha-3 example (TUR) and restates the offset/next_offset relationship and the 'one country reads no offset' rule, which mostly duplicates the schema text rather than extending 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 domain (country intelligence for export finance) and then splits the tool into two clearly delineated modes: an index when iso3 is omitted and an in-depth single-country record when it is supplied. Each mode's payload is enumerated (risk score, gap components, indicators, memberships with legal citations, reference events, team deals), so an agent knows exactly what resource is being fetched and in which shape.

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 when-to-use rule is explicit and parameter-driven: omit iso3 for the covered-country index, pass a three-letter code for one country. It also explains the pagination path (read output_cap's next_offset, feed it back as offset) and warns not to interpret zeroed deal fields as 'no deals'. It stops short of naming sibling tools (e.g. company_profile, entity_risk_profile) or stating when a different tool is the better choice, which keeps it below a 5.

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