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

Given annotations include readOnlyHint=true, the description adds value by stating the data is 'live' and 'fresh from the X API,' and it discloses the behavior of returning a link when no account is connected. This goes beyond the annotation's read-only hint and provides useful context about data freshness and the no-account case.

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 a single, well-structured sentence that front-loads the core functionality and includes a practical instruction. It avoids redundancy and stays concise while providing necessary context.

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 simple, read-only tool with one optional parameter, the description is complete. It covers what data is returned, mentions the live nature, and includes the no-account handling. Since there's no output schema, it could detail the return format, but the key information is present.

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 covers the single optional parameter 'handle' with full coverage (100%), so the description doesn't need to add much. It adds a small clarification that omitting returns all connected accounts, which is slightly more than the schema's 'Omit for all connected accounts,' effectively reinforcing it. Baseline 3 is appropriate.

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 it retrieves live profile stats (name, handle, follower/following counts, tweets) for connected X accounts. It distinguishes from siblings like get_my_tweets and get_twitter_following by focusing on profile stats, not tweets or following lists.

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 explains how to handle the case when no account is connected (give the user the link returned), which is a clear condition. It doesn't explicitly name alternatives like get_my_tweets, but the tool's specific purpose makes it obvious when to use it.

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