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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description goes well beyond them: it enumerates the cascade (recipient assignment, marketing-campaign targeting, installation records), clarifies what does NOT happen ('Scribe does not push an uninstall to mailboxes it was already installed in'), states the required scope, and predicts the 404 on an unknown id.

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 most consequential fact (permanent, no undo or trash) is front-loaded in the first clause, followed by cascade details and then routing alternatives. Every sentence carries distinct information with no filler, appropriate length for a destructive cascade operation.

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?

With an output schema present, return values need not be explained; the description still covers the operation's permanence, side effects, scope requirement, failure mode, and tool-selection boundaries. Nothing an agent needs to invoke this safely is missing.

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 description coverage is 100% and both parameters are fully documented in the schema, including the 'only primary templates can be deleted' caveat and the context-writing rules. The description's 'by UUID' and 404 note largely restate the schema, so it adds marginal value here — baseline 3.

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 ('Permanently delete a signature template by UUID') and immediately distinguishes itself from sibling deletion tools like delete_signature_variant. An agent can identify exactly what this deletes and how it differs from remove_signature_recipients 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?

Explicitly conditions use: 'Use it only when the template itself should go', then routes to the correct alternatives with their own conditions — remove_signature_recipients/remove_signature_recipient_entities for narrowing reach, delete_signature_variant for resetting a single variant. When-not guidance and named alternatives are both present.

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