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

With no annotations supplied, the description carries the full burden and discloses important behavior: read-only operation, default `months` of 18, imported visits counting, exclusion of customers with open jobs or upcoming visits, permission scope ('Owner or office'), and the returned row fields. It also describes counts for uncontactable customers and shows the email that would be sent. This is rich behavioral context beyond what the schema provides.

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 'Win-back list' and every clause adds useful information about filtering, exclusions, returned fields, and permissions. It is dense and somewhat run-on, but does not waste space on restating schema or annotations. Slightly clearer sentence boundaries would improve structure.

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?

Given an output schema exists, the description does not need to explain return values, yet it helpfully lists the row fields and contactability counts. It covers the core behavior, exclusions, permissions, and sibling distinction. The remaining gaps are pagination/cursor semantics for `after` and `limit`, and whether filters combine, but overall it is complete for a read-only query tool.

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 13%, so the description must compensate for largely undocumented parameters. It adds meaning for `months` (default 18), `job_type` (filter by job type words), `tag`, and `has_plan`, and implies `title` relates to the email content. However, `after` and `limit` are not explained, leaving key pagination/filter mechanics unclear.

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 resource and verb-like action: a win-back list of customers with no visit in `months`, excluding open jobs and upcoming visits. It also explicitly names the sibling tool `customers.winBackQueue` and distinguishes its read-only role from sending. An agent can identify exactly what this tool returns and how it differs from the nearest alternative.

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 usage context by saying it is read-only and that `customers.winBackQueue` sends, which routes an agent between previewing and acting. It also names the filters for selecting a subset. It does not explicitly state when to choose other sibling list tools like `customers_list` or `customers_audience`, so it falls short of full alternative guidance.

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