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 idempotency ('retries return the same result'), a ten-minute invitation expiry, a permission requirement ('requires kettle permission'), cost ('free, no postage or payout'), and privacy of shared words/cups. What it omits is failure behavior when the invitation has expired or the caller lacks permission.

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?

Five short sentences, front-loaded with the precondition, then parameters, then behavior, then permissions and privacy. No filler, and each clause adds a distinct operational fact.

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 3-required-param mutation with no annotations and no output schema, the description covers cost, idempotency, expiry, auth, and privacy. It still leaves the origin of 'boilId' and the success/return shape (what 'cups' means) unexplained, which matters given there is no output schema.

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 0%, so the description must compensate for all three params. It adds real meaning for 'word' (1-24 characters, no links) and 'requestId' (UUID, retry-idempotent), but says nothing about 'boilId' beyond the schema's UUID format, leaving the agent without guidance on where it comes from. The stated 1-24 character limit also conflicts with the schema's maxLength of 256.

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 ('Join a Kettle of Two boil') plus the gate condition (only when this account was invited), which is far more than a restatement of the name. It also draws a boundary against adjacent capabilities ('does not enable starting or cancelling boils'), though it never names a sibling such as kettle_status or pot_contribute.

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 gives the activation condition ('only when this account was invited') and an exclusion ('does not enable starting or cancelling boils'), which steers the agent away from misuse. It stops short of pointing to the alternative tool to use when the caller is not invited.

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