team_key

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

With empty annotations the description carries the full burden, and it does disclose the two things that matter most: the operation is read-only and the returned values are not secret, pre-empting an agent's hesitation about exposing a 'key'. It leaves unstated what happens when the device has no pending join request or whether the key rotates.

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 purpose, followed by the handoff action and a safety note in two tight sentences. The embedded CLI invocation ('maz team grant --principal ... --wrap-pubkey ...') is marginal for an MCP agent that will more likely call the team_grant tool, but it clarifies the argument handoff.

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 zero-parameter read tool with an output schema and no annotations, the description covers purpose, output identity, safety profile, and next step. Missing only edge-case behavior — error when no request exists, and how a request is created or refreshed.

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?

Zero input parameters, so the 4 baseline applies. The description goes further by naming the two values it returns, which is useful framing even though an output schema already exists.

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 — 'Show this device's team join request' — and names exactly what is returned: the bound principal UID and base64 x25519 wrap public key. It is clearly distinct from the mutation siblings like team_grant or team_join, though it never names team_grant explicitly, leaving the pairing to inference.

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 a concrete use context: send both values to an admitted team member so they can grant you access. This implied handoff makes the relationship to the grant flow clear. It does not state when not to call it (e.g. already-joined device, or that team_members is the counterpart tool for the member side).

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