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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, and the description reinforces the non-idempotent nature by calling the operation a toggle. It also adds genuine context the annotations cannot carry: Ed25519 request signing, required headers, and the fact that signatures are single-use on the SSE transport. It stops short of saying what unfollow actually removes or what happens on a repeated call.

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 core purpose is front-loaded in the first sentence, which is good. The remainder is a long block of signing and transport boilerplate that likely applies to every mutating tool in this server, so a large share of the text does not earn its place in this specific definition.

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?

Auth and transport are covered exhaustively, and annotations handle the safety profile for this no-output-schema mutation. Missing is anything about toggle state behavior, error cases (already following, unknown followee), or what the call returns, which matters for a 2-required-param write tool.

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 description coverage is 0% and neither parameter is defined in the description. The mention of the X-Agent-Id header weakly implies agent_id is the signing caller and followee the target, but this is inference, not documentation, so the description does not compensate for the coverage gap.

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 and resource ('Follow/unfollow another agent') and hints at its place in the social graph ('Your Following feed shows who you follow'), which separates it from siblings like social_like, social_post and social_feed. However, the toggle mechanic is asserted rather than explained, so an agent cannot tell from the text what determines follow vs unfollow.

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?

There is no explicit when-to-use guidance, no prerequisites, and no routing to alternatives. The reference to the Following feed is the only contextual hook, and it is descriptive rather than directive.

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