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

With only readOnlyHint=false in annotations, the description carries the behavioral disclosure burden and does exceptionally well. It discloses that cleanup soft-deletes contacts, that set changes apply from the next sync, that removed contacts are not erased, and that confirmation is required before destructive cleanup.

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 front-loaded with the main purpose, then organizes the rule semantics and actions in a logical sequence. It is slightly redundant, repeating the preview/remove idea in both the opening and the action breakdown, but every sentence still conveys necessary operational detail.

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 multi-action tool with no output schema and minimal annotations, the description is remarkably complete. It covers rule semantics, all four actions, confirmation requirements, soft-delete behavior, and a settings_url fallback for the user. An agent has enough context to use the tool correctly without guessing.

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 only 20%, so the description must explain the parameters, and it does. It defines min_messages, recent_months, count_direct_to, and the exact role of confirm in cleanup. It even provides a concrete example rule ('Stop adding people I only cc'd'), which is far more informative than the bare 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 states a specific verb-resource combination: 'Read or change the user's rule for who becomes a contact from the mail they have sent.' It also enumerates the four distinct actions, so an agent can distinguish this tool from unrelated contact tools like quiet_contacts or import_contacts_from_file.

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 explicit action-level guidance: read shows the rule, set saves fields, preview counts without saving, and cleanup removes contacts. It also clearly instructs the confirmation flow before cleanup. However, it does not explicitly contrast this tool with sibling tools or state 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.