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

Annotations already cover readOnlyHint, destructiveHint=false, and openWorldHint, so the safety profile is set; the description still adds real context beyond that — the exact enumeration of per-person permission values, the 'has opened it yet' signal, and the important semantic that the list governs site access only in invite-only mode. It stops short of noting auth requirements, ordering, or pagination behavior, which keeps it out of 5 territory.

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?

Two sentences, front-loaded with the core action and payload, with the conditional access-gating caveat placed after the essentials. The second sentence is somewhat dense with nested clauses ('which it does only while the site is invite-only'), costing a little readability, but no sentence is filler.

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 one-parameter read tool with an output schema, the description covers the important ground: what the list contains, what each entry carries, and the invite-only caveat that would otherwise mislead an agent into treating the list as an ACL. Empty-state behavior and any access prerequisites are the only notable omissions.

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?

There is a single required parameter ('site') and the schema description coverage is 100%, with the schema itself telling the agent to source it from list_sites. The description adds no format or sourcing detail beyond that, so the 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?

The description names a specific verb and resource ('Lists the people on a site's list') and immediately disambiguates what that list is by tying it to 'the ones invite_people added'. It also previews the payload — permission level (`view` or `comment`) and whether each person has opened it — so an agent can tell this apart from siblings like list_comments, list_folders, and list_sites 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?

It establishes clear usage context by anchoring the tool to invite_people as the writer and clarifying the condition under which the list is authoritative ('only while the site is invite-only'). It doesn't name an alternative to use instead when the site is public or when you want site metadata rather than collaborators, so there are no explicit exclusions.

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