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

Beyond the annotations (which indicate a non-read-only, non-destructive mutation), the description discloses that the profile and its posts remain searchable, that only the refresh stops, and that it is free to call. It also specifies the not_found error behavior, which the annotations do not cover, adding significant transparency.

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 front-loaded with the core action and keeps most sentences short. However, it repeats 'free' twice ('Free to call' and 'Cost: free'), which is slightly redundant but not misleading.

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 one parameter and no output schema, the description covers all essential aspects: what happens to the data, cost implications, error response, and input provenance. For a tool of this simplicity, it is 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?

The schema already documents profileId with 100% coverage, so the baseline is 3. The description adds value by specifying the source of the ID (list_tracked_profiles or search results) and clarifying it is internal, which helps the agent obtain the correct value.

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 uses the specific verb 'Stops monitoring a profile' and clarifies the resource and key consequence (no further scheduled refresh crawls are charged). It distinguishes itself from sibling tools like track_profile by framing the action as stopping a recurring process, not deleting data.

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?

It tells the user to pass the internal profileId from list_tracked_profiles or search results, and explains the not_found return case for a profile not currently monitored. While it doesn't explicitly name alternatives like track_profile, the context makes the usage scenario unambiguous.

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