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

Annotations already cover read-only/idempotent safety, and the description adds hard behavioral facts the annotations lack: 40 returned by default, a maximum of 200, and that `count` is the total matched *before* the limit. That count-vs-returned distinction is exactly the kind of detail that prevents an agent from misreporting totals.

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?

Four dense sentences ordered purpose → alternatives → limits → id hand-off, with no filler or restatement of the title. Every sentence carries information an agent needs for a correct call.

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?

There is no output schema, but the description enumerates the returned fields and the `count` companion, and it discloses pagination limits and narrowing options. Nothing material for correct invocation is left unstated.

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; the description goes beyond it by stating that `id` is the key consumed by get_contact, update_contact, set_contact_field and enroll_in_sequence, and by tying `accountId`/`workspaceId` behavior together. It does not add filter syntax beyond the schema, keeping it at 4.

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 with a specific verb+resource ('List and filter the CRM contacts') and even defines the population ('people who have written to or interacted with the connected accounts'). It names the exact fields and the `count` value returned, so an agent knows precisely what this produces.

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?

It explicitly routes to alternatives: 'for one person's channels, custom fields and notes use get_contact, and for their messages list_conversations.' It also gives a follow-up rule when results are truncated ('if count is higher, narrow with tag, search, platform or accountId').

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