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

Given annotations declare readOnlyHint and destructiveHint, the description adds valuable context beyond that: it explains that results come from regular reports with rolling refresh (delays possible), that no AI runs are made, and clarifies the semantics of 'brand_in_answer' (null means not established, not no). This is useful behavioral context not in the schema or annotations.

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 well-structured with a clear opening line, a detailed explanation of what is meant by 'tracked articles' and the output fields, and a separate arguments section. It is somewhat lengthy but each sentence adds value, and it avoids fluff. The main behavior is front-loaded, with the distinction from get_articles placed near the end for clarity.

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 read-only tool with no output schema, the description covers the key aspects: what the tool returns (fields like article_cited, previously_observed, providers, brand_in_answer), the meaning of null, the data freshness caveat, and the distinction from the sibling. It lacks detail on pagination or sorting, but given the complexity, it is fairly complete.

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 only 33%, with the domain parameter having no description. The description explains domain as 'Only articles on this domain, e.g. resources.example.com', which adds crucial meaning beyond the schema. brand_id is described as 'The brand to read', which is minimal but sufficient. user_intent is not described but is an analytics hint, and the description's focus on the other two parameters compensates for the low schema coverage.

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 clearly states the tool reads the brand's tracked published articles and whether they are cited in AI answers, distinguishing it from get_articles which lists drafts. It is specific about the resource (tracked articles) and the action (read).

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 description explicitly differentiates from the sibling get_articles, noting that get_tracked_articles is for tracked published articles, not drafts. It also mentions the rolling refresh cadence, which helps set expectations on when to use it (e.g., not for real-time checks).

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