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

Goes beyond the annotations by disclosing two non-obvious behaviors: the post-join capability (reading team-shared memories) and the failure mode where an unsupported plan refuses the invitation but leaves it open for later retry. It does not describe permission requirements or the response shape, but the plan-gate disclosure is meaningful context that annotations cannot convey.

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?

Three short sentences, each carrying distinct information: what it does, the positive outcome, and the gated failure case. The core action is front-loaded and no sentence is redundant.

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 single-parameter mutation with an output schema absent, the definition covers purpose, precondition, outcome, and a failure mode, which is close to sufficient. Missing only return-value or post-join state details that an agent might want confirmation of, though the idempotent annotation reduces that need.

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?

With one parameter at 100% schema coverage, the schema already explains that the token is the invitation ID from the email. The description restates this as 'using the invitation from the email sent to you' without adding format, source, or error-handling detail beyond the schema.

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: joining a team via an invitation token from an email. The phrase 'you were invited to' makes the direction unambiguous, so an agent can tell this apart from muninn_team_invite (which sends invitations) and muninn_team_invites_list (which enumerates them).

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?

Clearly establishes the precondition — you must have received an invitation email with an ID — and notes the plan-gated case where the invite is refused. It does not name a sibling as the alternative (e.g., check muninn_team_invites_list when the token is unknown), which keeps it just short of explicit routing.

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