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

Goes well beyond the annotations by disclosing the dry-run preview (old and new value of every field, prompting where the client supports it, otherwise token-scope fallback), the hard refusal for Terraform-managed groups, the non-retroactive semantics of alert_as_one, and the scope requirement on channel_ids. Annotations only say destructive/idempotent; the description explains what is actually destroyed and what is refused.

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?

Front-loaded with the verb and the enumerated mutable fields, then constraints. The long parenthetical describing alert-as-one is dense but carries real semantics; a few clauses (e.g., restating channel_ids replacement already in the schema) could be trimmed without loss.

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 an output schema already covering returns, the description supplies everything else an agent needs: confirmation/preview behavior, scope fallback, Terraform refusal, and retroactivity rules. Nothing material is left for the agent to guess.

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 100%, so baseline is 3, but the description adds genuinely new parameter-level meaning: channel_ids requires the channels:read scope, and alert_as_one is explicitly non-retroactive for already-open incidents. The explanations of alert-as-one fan-out and alert_again largely restate the schema descriptions, keeping it below a full 5.

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 (change) and resource (monitor group) and enumerates exactly which fields are mutable: name, alert-as-one, channel set, reminder interval, alert_again. An agent can distinguish this from update_monitor and list_monitor_groups without opening any 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?

Gives concrete gating context: Terraform-managed groups are refused outright, channel_ids requires the channels:read scope, and turning alert-as-one on/off only affects failures that start afterwards. It does not name a sibling alternative (e.g., update_monitor for individual monitors) or state exclusions for when not to use it, so it stops short of a 5.

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