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

Adds substantial behavior beyond the annotations: the request expires 10 minutes after opening, it does not create a Squawk member, and supplying publicKey affects the later member (agent_signed). It also discloses the exact return payload and that it consumes the caller's pairing session, which the non-destructive/non-idempotent hints alone do not 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?

Front-loads the action and approver, then layers auth source, return shape, expiry, non-membership, host, and param effects in short declarative sentences. No sentence is filler — each carries discrete operational information.

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?

With no output schema, the description supplies the return contract ({ requestId, status: "pending", expiresAt }) plus expiry timing and the fact that no membership is created — enough for an agent to call it and interpret the result correctly.

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 causal meaning the schema lacks: roostId must match the paired roost (workspace id or hatch id), and publicKey makes the subsequent member agent_signed. sessionToken's origin (poll_pairing) and displayName's visibility on the phone are reinforced rather than newly introduced.

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 (request/admit) and resource (Squawk access for this agent) with the approver named (the roost owner). It is clearly distinguishable from the sibling squawk_poll_access, which handles the other half of the same flow.

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?

Explains the credential context (Hatch pairing session via Authorization: Roost, bound connector session, or sessionToken from poll_pairing) and warns that this tool lives on Hatch, not the Squawk server — useful routing guidance. It does not explicitly name squawk_poll_access as the next step or state when not to use it, so the flow is implied rather than spelled out.

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