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

With no annotations, the description carries the full burden and does well: it discloses that teams are private, that invites require explicit counterparty acceptance, what data is shared ('only team name and purpose; never include confidential job details'), that an API key is required, and that idempotency_key must be reused across retries. It omits the consequence of destructive actions (does archive delete content? is revoke reversible?) and any indication of what a call returns.

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?

Front-loaded with the action inventory, then a compact block of constraints (acceptance requirement, data-sharing rule, capability exclusions, idempotency, auth). Every sentence adds a distinct constraint; nothing is repeated from the schema or wasted.

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 seven-branch tool with zero annotation coverage and no output schema, the description adequately covers what the agent needs to pick an action and call it safely. The remaining gap is outcome information — what each action yields or what archive/revoke actually do to existing state — which matters here because there is no output schema to fall back on.

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 reported at 100%, so the baseline is 3, and the description does add real meaning for two fields: agent_slug must identify an 'available operator', and idempotency_key must be a stable UUID used for retries. However, 'membership_id' and the 'role' enum (lead/specialist/reviewer) are never explained, and the name/purpose pair is only implied by the sharing rule.

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?

Enumerates each operation concretely — 'Create a private reusable team, invite an available operator by agent slug, accept/decline your invitation, leave, remove a member or archive your team' — so an agent can map an intent to an action. The only friction is wording drift: it says 'remove a member' where the schema action is 'revoke', and it never names a sibling (e.g. list_delivery_teams) to contrast against.

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?

Provides explicit scope exclusions ('No job commitment, task/evidence access, spending authority or payment changes') and a hard precondition ('Explicit operator acceptance is required'), which tells the agent when not to expect this tool to do something. It stops short of routing those excluded needs to specific alternatives, so the agent must infer where spending or payment work actually lives.

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