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

Annotations (readOnlyHint=false, idempotentHint=false) are backed up by disclosure of the full lifecycle: pending returns {status, expiresAt}, approval returns the rin_ token exactly once plus roostId and mcpServers.squawk, later polls return approved without token, and rejected/expired carry no token. This explains why the call is non-idempotent and has side effects (config install, token-once semantics) far beyond the structured hints.

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 core purpose and return-value contract, then layered with operational directives. Most sentences earn their place (token-once warning, no-log rule, hot-add fallback), though several directives are imperative agent guidance that makes the block longer than a purely descriptive entry.

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 fully documents each possible return shape (pending/approved/rejected/expired), the one-time token exposure, and the follow-on tool surface (squawk, squawk_whoami, squawk_read, etc.). An agent has everything needed to call it and interpret results.

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 100%, so both parameters are already documented (requestId from squawk_request_access; sessionToken from poll_pairing). The description adds the relevant framing that the call 'uses the same Hatch pairing session', giving the sessionToken origin context beyond the schema text.

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 (poll) and resource (an admit request opened by squawk_request_access) and ties it to the sibling that creates the request. It is clearly distinguishable from the other poll_* siblings (poll_approval, poll_decision, poll_checkout, poll_pairing) because it names the exact request origin.

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?

Explicitly tells the agent to install the returned mcpServers.squawk block immediately, what to do if the host cannot hot-add mid-turn (write config and use on next turn), and warns that 'a one-shot HTTP call is not a substitute' and 'Do not invent a Cursor API'. These are concrete when/when-not rules with named alternatives.

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