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

Annotations already flag destructive and non-read-only behavior, and the description adds substantial behavioral detail: channel_ids/tags replace entire sets, an empty channel list silences the monitor, Terraform-managed monitors are refused, and the tool shows old/new values before executing or falls back to running on the token's scope. This goes well beyond the annotation flags and matches destructiveHint.

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 dense and well-structured: primary purpose and editable fields first, exclusions second, runtime behavior last. The trailing 'Not read-only' is mildly redundant with the annotations, but every other sentence earns its place and no significant content is missing.

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 9-parameter mutation tool with a full input schema, output schema, and annotations, the description covers the invocation-critical gaps: destructive replacement semantics, Terraform refusal, auth scope, and prompt behavior. An agent can use this tool correctly without opening the schema for most decisions.

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 the baseline is 3, but the description adds one genuinely schema-absent fact: channel_ids requires the channels:read scope. It also translates parameter names into readable concepts (e.g., 'reminder interval' for renotify_interval_secs), though most details are already present in the schema.

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 opens by explicitly stating the tool's function—'Change how loudly a monitor is watched'—and enumerates the specific mutable settings (check interval, alert confirmations, tags, channel_ids, region quorum, etc.). It further distinguishes itself from siblings by listing what it refuses to change (name, address, assertions, owner), making its scope unmistakable.

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 description gives clear negative guidance: it cannot change what the check watches and refuses Terraform-managed monitors, so an agent knows when this tool is not appropriate. It does not explicitly name an alternative tool or instruct calling get_monitor first, though the schema's parameter descriptions partially cover that need.

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