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

Annotations cover only the safety profile (readOnly, non-destructive, closed-world), so the description carries the rest and does it well: it discloses the return shape {results:[{id,title,text}]}, the dedup behavior (identical campaigns collapsed into one row), and the non-obvious empty-result behavior (a plain note with a dashboard link rather than an empty array).

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 verb and scope, and most sentences carry distinct information (query kinds, return shape, empty case, fetch handoff). The example questions and the closing line about ChatGPT Deep Research / Claude research modes are decorative padding that slightly dilutes density.

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 no output schema, the description correctly supplies the response shape and the empty-result case. It stops short of stating result-count limits, ranking, or pagination behavior, which an agent issuing a broad query would benefit from knowing.

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% and there is a single parameter, so the schema already documents query fully. The description restates essentially the same text as the parameter description (query kinds, return shape, 'not a web search') rather than adding syntax, format, or length constraints beyond it, making the 3 baseline correct.

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 (Searches) and specific resources (this account's brands and campaigns, plus Rebbel help/pricing/setup pages), and explicitly rules out a plausible misread with 'Not a web search.' It also distinguishes itself from the sibling fetch by explaining that fetch retrieves the full record for an id.

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 the agent to the alternative (fetch) with the condition ('Pass a result's id to fetch for the full record') and gives an exclusion ('Not a web search'). It does not, however, contrast with the many list_* siblings (list_brands, list_campaigns) that an agent might otherwise pick for browsing the same data.

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