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

Annotations mark destructiveHint true, but the description adds valuable behavioral context: side effects (publisher domain added to outreach shortlist, brand's own site not), cost transparency (uses brand's regular reports, costs nothing extra), and idempotence (tracking an already-tracked URL changes nothing). It also clarifies that past observations are kept on stop, which is not obvious from 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 long but well-structured with bullet points for actions and a separate Args section. It is front-loaded with the three actions and their conditions, and every sentence adds value (side effects, prerequisites, cost). The length is justified by the tool's complexity, but it could be slightly tightened by moving the access requirement earlier.

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 8 parameters, 3 actions, and no output schema, the description covers the essentials: prerequisites, side effects, how to read results, and validation hints. It doesn't describe error handling or return values, but since no output schema is provided and the tool likely returns a status, the pointer to get_tracked_articles is sufficient. The description is comprehensive enough for an agent to call it correctly.

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?

The description explains the semantics of all parameters except user_intent, which is already described in the schema. It adds clarity on required vs optional (url required for 'track', article_id or url for stop/restore), format constraints (published_on YYYY-MM-DD not in future), and limits (prompt_ids up to 20). Given low schema coverage (13%), the description compensates well.

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 manages tracked articles with three specific actions (track, stop, restore), each with a clear verb and resource. It explicitly differentiates from get_tracked_articles by directing the user there for reading results, and it distinguishes the scope of tracking (guest posts, brand site) and the side effect of adding publisher domains to an outreach shortlist.

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 provides explicit guidance for when to use each action, including prerequisites (editor access to a paid brand), constraints (URL not a homepage, max 20 prompts), and points to the sibling tool for reading results. It also notes that tracking a URL already tracked changes nothing, which prevents redundant calls.

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