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

Annotations declare a non-read-only, non-destructive, closed-world operation, and the description adds genuinely new behavior: the human completes sign-in out-of-band via a returned url and the agent must relay both url and tellUser. That hand-off pattern is not inferable from annotations or schema. It stops short of saying what happens to an existing connection or how long the pending state lasts.

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 action and the target services, then the return contract, then conditional parameter rules. Dense but each clause carries information; it is slightly crammed into three long sentences but wastes nothing.

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?

An output schema exists, yet the description still supplies the agent-facing next action (show url + tellUser, then poll get_setup_status), which is the piece the schema cannot convey. With 4 params at full coverage and annotations present, nothing needed to call this correctly is missing.

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 the baseline is 3; the description earns above that by mapping each optional field to its service (Zendesk→subdomain, Gorgias→account, Shopify→shop) and clarifying that omission is safe because the dashboard page will prompt. That conditional-omission semantics is real added meaning.

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?

Opens with a specific verb and enumerated resources ('Start connecting Gmail, Shopify, Zendesk, Front or Gorgias'), and the return-value sentence pins down what the call produces (a dashboard url). An agent can separate this from list_integrations or set_up_helpdesk without opening the schema.

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?

Gives clear follow-up routing: check get_setup_status once the user finishes, and set_up_helpdesk completes a helpdesk afterward. It also says to pass subdomain/account/shop 'when known; otherwise the page asks.' What's missing is any exclusion — e.g., what to do if the service is already connected.

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