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

Annotations already declare non-read-only, non-destructive, idempotent behavior, so the bar is lower. The description adds real value by explaining the side effect (writes into your private feed), but stays silent on what happens on repeat follows, whether the follow can be undone, and what a missing/invalid target yields.

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?

A single sentence with the action and its payoff front-loaded, plus the endpoint inline. Nothing to trim and nothing buried.

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 two-parameter mutation with no output schema, the essentials are present but thin: the agent still can't tell how to identify the target, whether re-following is a no-op, or how to reverse it. Adequate, not 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 50%: idempotency_key is documented in the schema, target_id is not. The phrase 'record/project' hints that target_id accepts either entity type, which is genuinely useful, but no format, prefix, or constraint is given to compensate for the undocumented parameter.

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?

States a specific verb (follow) and resource (record/project) and names the observable effect — changes appear in the private feed, with the endpoint given. Clear against most siblings, though it doesn't explicitly disambiguate from collaboration_subscribe, which sounds adjacent.

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 mention of the private feed implies when this is useful (you want change notifications), but there is no explicit when-to-use vs. when-not, no prerequisite (must the target exist? can you follow anything?), and no pointer to an unfollow counterpart.

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