Invite jurors

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

Annotations only say readOnlyHint=false, destructiveHint=false, so the description carries the behavioral burden and exceeds it: it reveals the no-accept-step seating behavior, the independent per-invitee processing, the duplicate/not_found reporting, and the privacy-critical shareUrl behavior for private cases. That shareUrl disclosure is the kind of behavioral context annotations never encode.

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?

The description is dense but every sentence earns its place; the most actionable constraint (owner/admin required, at least one of invitees/tribeId) is front-loaded. It is somewhat long relative to typical tool descriptions, but given the non-obvious seating behavior and the private-case shareUrl pitfall, the length is justified rather than padded.

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 write-like tool with no output schema, the description covers prerequisites, parameter selection rules, per-invitee outcome reporting, and the response's shareUrl nuance. There are three parameters, all documented in both schema and description, and no enums or nested objects. Nothing an agent needs to invoke this correctly and use its output well is missing.

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 already 100%, so the baseline is 3, but the description adds meaningful semantics: invitees are processed independently with per-entry outcomes, tribeId behavior is expanded to 'every current member plus the chieftain', and the response's shareUrl semantics for private cases are explained. It tells the agent that for a private case, giving the bare url 404s, which is decisive for how the agent uses the returned values.

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 and resource — 'invite users to the jury of a case you own (owner or admin only)' — and immediately distinguishes the tool from sibling jury tools like tribeunal_join_jury and tribeunal_jury_duty_accept by framing invitations as recruitment, not acceptance. It clearly differentiates from tribeunal_invite_tribe_members by targeting case juries rather than tribes.

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?

States explicit preconditions: ownership/admin on the case, and membership/ownership/admin on the tribe. It explains when to use tribeId vs invitees, that at least one is required, and gives a clear when-not: opening the case page seats the invitee as a normal juror without a separate accept step. This makes selection against the sibling jury tools unambiguous.

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