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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds non-obvious behavior beyond that: the two-call confirmation protocol and the downstream effect that attached sites regenerate unwritten articles. It stops short of saying whether changes are reversible or what the summary contains.

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?

Three sentences, each carrying distinct information: scope of change, side effect, and the confirmation protocol. The destructive/confirm warning is front-loaded in the final position where it belongs before invocation.

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 mutation with six parameters, no output schema, and partial schema coverage, the description covers the calling protocol and side effects well. It still omits whether omitted fields are left untouched or cleared, and whether the token expires — details that matter for a destructive write.

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 only 33% (only site and confirmToken are described), so the description must compensate — and it does, naming all three optional mutable fields (name, rules, enabled) and restating the token's two-phase semantics. The required guardrailId remains unexplained by both schema and description, leaving one real 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 ('Changes a library guardrail's name, rules or enabled flag'), and the word 'library' plus editable fields distinguishes it from create_guardrail and delete_guardrail. What is left implicit is the boundary with update_site_guardrails, which an agent must infer from the name alone.

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 confirmToken instruction is a genuine usage pattern ('first call returns a summary and a confirmToken; call again with confirmToken to proceed'), which tells the agent how to invoke deliberately. However, there is no explicit statement of when to prefer this over delete_guardrail or update_site_guardrails, so the choice among guardrail tools is left to inference.

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