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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description goes well beyond them: it spells out the replacement semantics (omitted ids are dropped), the downstream effect ('Future articles are regenerated against the new rules'), and the non-obvious two-phase confirmation handshake that the annotations cannot express. This is exactly the extra context a destructive mutation needs.

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 dense sentences, front-loaded with the destructive replacement behavior before the execution flow. No filler, no restatement of the title or name.

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, non-idempotent mutation with no output schema, the description covers the essentials: what is overwritten, what happens afterward, and how the confirmToken flow works. The only real gap is where the guardrail ids originate, but that is a discovery detail rather than a call-correctness one.

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 67%; site and confirmToken are already documented, but guardrailIds carries no schema description. The prose compensates by defining the array as an exhaustive keep-list rather than an additive set, which is the one piece of semantics a caller could get wrong. It stops short of clarifying that ids must come from the library guardrail set.

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 ('Replaces the COMPLETE list of library guardrails attached to this site') and emphasizes full-set replacement, which cleanly separates it from sibling update_guardrail (single guardrail edit) and get_site_guardrails (read). An agent can select it without opening the schema.

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?

'send every id that should stay' tells the caller how to construct the argument, and the two-step confirm instruction ('call again with confirmToken to proceed') tells them how to execute it. It gives clear context but never points at get_site_guardrails for retrieving the current list, so the obvious prerequisite for a full-replacement call is left implicit.

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