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

Beyond the readOnly/idempotent/closed-world annotations it discloses the failure semantics that matter most: a multi-country brand without a market is 'listed as unavailable with the markets to choose from, never guessed.' It also bounds the output ('aggregates only: no campaign list, subject lines, offers or creative analysis. There is no open, click or revenue data') and states a citation obligation via details_url.

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-loaded with the core action and what is returned, then usage, then edge cases — a sensible priority order. It is dense but nearly every clause carries information; the quoted user-phrase examples are long but directly serve tool selection. Slightly heavy as a single paragraph, hence 4 rather than 5.

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?

With an output schema present, the description needn't detail return values, yet it still characterizes them (aggregates only, no engagement or revenue metrics) and closes the remaining gaps: the verbatim-name rule, the market disambiguation behavior, the 5-brand cap, and the sourcing requirement. Nothing an agent needs to call this 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 prose adds real meaning: brand names should be passed verbatim as the user wrote them, market is a country (SE/NO/DK/FI/DE or country name) and explicitly 'not a topic or category', and from/to must start within the last six months — a constraint the schema does not encode. This goes modestly past the schema rather than re-stating 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?

States a specific verb and resource ('Compare 2 to 5 ecommerce brands side by side in ONE call') and immediately enumerates exactly what is compared: current frequency, emails observed in 6 months, first-observed date, latest campaign date, and market rank. It explicitly distinguishes itself from the sibling get_brand_summary ('Use this instead of calling get_brand_summary repeatedly'), so an agent can route without inspecting 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?

Gives concrete trigger examples ('Compare Mio, IKEA and Westwing', 'Who emails more, Boozt or Zalando?'), names the alternative to avoid (repeated get_brand_summary), routes discovery to find_brands, and handles the overflow case ('More than 5 brands: call again with the rest'). When-to-use, when-to-use-something-else, and batching behavior are all covered.

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