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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond: the 25-per-page cap and offset paging, that the product figure is a count and never stock or pharmacy holdings, that sorting is never sponsorship-driven, and that a listing is not an endorsement. These are non-obvious behavioral and semantic constraints an agent could not infer from structured fields.

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?

Front-loads purpose, then return shape, then caveats, then sibling routing — a logical order with no filler. It is dense and slightly long, packing paging, ranking and disclaimer into one block, but nearly every clause carries distinct information.

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?

Despite an output schema existing, the description still names the returned fields (slug, URL, town/country, website, product count), plus paging and ranking semantics. For a 5-parameter zero-required search tool, nothing an agent needs to invoke it correctly 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%, so the baseline is 3, but the description adds real meaning: it frames `offset` as the paging mechanism returning the next offset, and characterizes `category` as 'the dose forms they make'. It does not re-explain `limit` or `sort` enums, so it stops short of the schema's full detail.

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?

Opens with a specific verb and resource ('Find the brands (makers) of cannabis-based medicines'), clarifies the search axes (name or dose form), and explicitly distinguishes itself from get_listing and find_products. An agent can identify the tool's niche among the nine siblings without opening the schema.

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 routes: use get_listing with kind "brand" for one brand in full, and find_products with the brand name as `query` for its products. It also implies the browse case via the schema ('omit query to browse') and the pagination continuation. When-to-use and when-not-to-use are both covered.

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