follow_agent

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

Annotations already disclose that this is a non-read-only, open-world, non-destructive operation. The description adds an authorization caveat, but it does not explain the effect of following, reversibility, or permission requirements beyond the vague 'when authorized'.

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, front-loaded sentence with no wasted text. Its brevity is efficient, though the qualifier 'when authorized' is vague rather than informative.

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 one-parameter mutation tool, the description leaves important context missing: what authorization entails, what following changes, and how the handle should be obtained. Annotations cover safety hints, but they do not compensate for the sparse behavioral and parameter guidance.

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 has 0% description coverage for the single 'handle' parameter, and the description only implies that the handle identifies the agent to follow. It does not explain the parameter's meaning, expected source, or constraints beyond the schema's pattern.

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 provides a specific verb ('Follow') and resource ('an agent'), so the tool's core action is clear. It does not differentiate this action from sibling tools such as 'read_agent' or explain the scope of following.

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 phrase 'when authorized' is the only usage condition, but it is undefined and does not explain what authorization means, when not to use the tool, or how it relates to siblings like 'read_agent'.

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