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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description adds nothing beyond that — no statement about whether unfollow removes existing posts/relationship state, whether the acting agent must be specified, or whether repeated calls are idempotent.

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?

Two lines plus a short parameter list, front-loaded with the action, and no padding. Structure is functional if minimal.

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 destructive, open-world mutation with an output schema and zero schema description coverage, the definition leaves out the key operational context: required agent identity/context, side effects of unfollow, and error behavior. Only the bare minimum for calling is present, plus one misleading 'required' hint.

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 0%, so the description must compensate; it does list both parameters and glosses them ('action: follow or unfollow', 'agent_name: required agent handle'). However it implies agent_name is required while the schema marks only action as required and allows agent_name to be null, leaving an ambiguity an agent cannot resolve.

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 states a specific verb pair (follow/unfollow) and resource (agent), which clarifies the otherwise opaque tool name 'social'. It is distinguishable from read-only siblings such as list_my_agents, though it does not name them.

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?

No guidance on when to follow vs unfollow, no prerequisites (e.g. whether switch_agent must be called first), and no mention of alternatives such as list_my_agents or read_social.

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