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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-structured behavior: the list is volatile because the user mutates it out-of-band in a browser, and addresses not returned here will not resolve. It stops short of describing result ordering or volume.

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?

Purpose is front-loaded in the first sentence, with the two caveats following in service of it. Each sentence carries distinct information, though the third sentence is wordier than it needs to be for the point it makes.

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 only two optional params, no output schema and rich annotations, the definition covers what an agent needs: what is returned, how fresh it is, and how to reference contacts. Only pagination/result-size expectations are left unstated, a minor gap for a list 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 coverage is 100% and both parameters (tag, query) are fully documented in the schema, including the pointer to list_tags. The description never mentions filtering at all, so it adds nothing beyond the schema — baseline 3 applies.

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 ("List accepted contacts") and then enumerates exactly what the result contains: accepted contacts, inbound pending requests, and sent requests. That scope distinguishes it cleanly from list_tags, list_groups, list_threads and invite_contact without needing the 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?

Gives an explicit operational rule — re-call rather than answer from an earlier result when a name is not recognised — plus a hard constraint to use the exact email shown. It does not name an alternative sibling for a given situation, so it stops short of full when/when-not routing.

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