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

Given that no annotations are present, the description carries the full burden of behavioral disclosure and largely succeeds. It explicitly outlines the `marketAccess` block's semantics, distinguishes it from a registration, and clarifies its exclusion from counts when Japan is involved ('both are true and the distinction matters'). The explanation is helpful, but slightly verbose; however, it does add crucial operational context beyond what structured data would capture. A slight deduction because the 'both are true' explanation, while clear, could be tightened.

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 front-loaded effectively with the core value proposition, and the prose is mostly efficient. However, the marketAccess explanation rambles a bit, especially the clause about 'precedes product approval and outlives individual products', which, while informative, feels a bit tangential. The description could be tightened by about 20% without loss of meaning.

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 no annotations and no output schema, the description does a strong job of clarifying return semantics (per-market counts, source registries, absent markets list). It clearly handles the common edge case of the `marketAccess` block. It doesn't describe the response header or pagination, but for a tool of this nature, the description provides enough context for an agent to use it correctly. A small deduction for not explicitly stating that the absence of all three parameters returns an error or a full list, although it's implied.

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%, covering all three parameters, so the baseline is a 3. The description reiterates the 'use exactly one of' pattern implicitly by calling it 'THE cross-market question', but doesn't add new semantics beyond the schema. Indeed, the parameters are straightforward aliases for manufacturer identification, so the description need not add more. Meets 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?

Clearly identifies the tool's purpose: answering a cross-market question with a specific verb and scope ('every market where this manufacturer IS registered and every market where they are NOT'). The description efficiently differentiates it from the sibling get_registrations by mentioning 'Prefer this over get_registrations...' It also provides a concrete example ('registered in Indonesia and Thailand, missing in the Philippines') to clarify the intended 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?

Explicitly directs when to use this tool over a sibling: 'Prefer this over get_registrations when the question is about market presence rather than individual products.' It also gives a clear exclusion condition ('a marketAccess block... is NOT a registration') and provides a cautionary note for a specific edge case. Very actionable.

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