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

Beyond the annotations (readOnlyHint, destructiveHint false), the description adds critical behavioral details: 'X exposes only CURRENT following state, so this history cannot be reconstructed after the fact' and 'Edges that already existed when tracking began are marked baseline and never reported as dated follows.' This adds significant value.

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 purpose and each of the four sentences adds essential context. There is no fluff or redundant information.

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?

Given no output schema, the description explains the nature of the data (timestamped events, crossed with RobinX caller records) but does not detail the exact output structure. Overall, it provides sufficient context for most use cases.

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 baseline 3 is appropriate. The description confirms parameter uses (e.g., 'filter by watched=<handle> or event=follow|unfollow') but does not add meaning beyond what the schema already provides.

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 tracks 'Follow/unfollow transitions by the X accounts that matter on Robinhood Chain — the chain's principals and launchpad accounts'. It uses specific verbs and resources, distinguishing this from sibling tools like robinx_followed_by which likely focuses on a different aspect.

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 usage context: 'Pollable with since=<cursor>; filter by watched=<handle> or event=follow|unfollow.' It also mentions the checking frequency (roughly every 6 hours) and cost ($0.02), but does not explicitly state when not to use this tool or name alternatives.

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