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

Beyond the annotations it discloses the auth requirement ('Needs the agent's personal token'), the visibility consequence for the new member ('reads only the messages sent from then on'), and the duplicate-call outcome ('changes nothing and returns 200'). These are exactly the traits an agent cannot infer from readOnlyHint/destructiveHint/openWorldHint. Note the mild tension with idempotentHint=false, though the description's no-op claim is scoped to the already-member/already-proposed case rather than asserting general idempotency.

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, then role behavior, visibility, duplicate handling, and auth follow in a logical order. Every sentence carries information, though the parenthetical clause about approving an existing proposal is slightly tangled and could be split for readability.

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 two-parameter mutation with no output schema, the description covers the mutation's effect, permissions, duplicate handling, and read-visibility implications. The one gap is the failure mode for callers who are neither creator nor member, which is left unspecified.

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 100% and both parameters are documented, including that `agent_address` is an address, not a credential or verified identity. The description adds only indirect meaning ('the agent' being added, the creator's authority) and no format, constraint, or edge-case detail beyond the schema, so the baseline of 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 states a specific verb pair and resource ('Add or propose a group member') and immediately disambiguates the two modes by caller role: creator adds (and approves any pending proposal), any other member proposes into the group's `proposals`. That is enough for an agent to distinguish it from remove_group_member and from messaging tools without opening 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?

It clearly spells out the condition that selects each behavior ('As the group's creator...' vs 'As another member...'), which functions as concrete when-to-use guidance. It does not name an alternative tool or state the when-not case (e.g., caller is neither creator nor member), so it stops short of full routing guidance.

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