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

Annotations already declare readOnlyHint=false, destructiveHint=false, and non-idempotency, so the description doesn't need to restate safety. It adds valuable context beyond annotations: the tool returns a short code, the agent must read the 'say' text aloud, and the owner approves on their phone at kisscode.ai. It could mention code expiration or error handling, but the core behavior and human-approval dependency are disclosed.

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 three compact sentences, front-loaded with the core action and immediately followed by the trigger phrase, return value, and next step. Every sentence earns its place with no repetition of schema or annotation data.

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 non-read-only tool with no output schema, the description explains the return value ("Returns a short code"), the required human action, and the polling follow-up with pairing_status. It leaves minor gaps such as code expiry, failure modes, and whether repeated calls create duplicate pairings, but an agent has enough to invoke and continue the flow 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 description coverage is 100%, so the input schema already documents every parameter, including the enum for kind and the optional persona object. The description hints at supported device kinds ("car, smart speaker, robot or other device") but adds no syntax or usage details beyond the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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 uses a specific verb and resource ("Connect a car, smart speaker, robot or other device to KissCode") and clearly distinguishes the tool from siblings by naming the follow-up tool pairing_status. An agent can immediately tell this initiates device pairing rather than querying status or managing agent profiles.

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?

It explicitly states when to use the tool ("Use this when the user says something like 'connect my car to KissCode'") and gives the exact next step: "Then call pairing_status every few seconds." This routes the agent through the full flow and names the alternative sibling for progress checks.

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