connect

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

Annotations only say readOnlyHint=false and openWorldHint=false, so the description carries most of the burden and does so well: it discloses that the Google path kicks off a browser sign-in and returns immediately rather than blocking, and that the next call succeeds after user approval. It also implies the tool emits instructions for key-based apps. It does not say whether connecting is idempotent, what happens on an existing connection, or how failures surface.

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 action, then the per-app variations, then the alternative and the safety rule. Every sentence carries information, though the phrasing around the key-storage command is slightly convoluted and could be tightened.

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 one-parameter setup tool with no output schema and minimal annotations, the description covers the branches (key apps vs Google OAuth), the async return behavior, the sibling alternative, and a security constraint. Only edge cases such as re-connecting or already-connected apps are left unspecified, which is a minor gap.

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% and the single enum parameter is fully enumerated in the schema, so the description need not restate valid values. 'One app this server uses' adds mild framing but no syntax or format detail beyond the schema, which matches the baseline 3 for a fully documented single parameter.

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?

'Connect one app this server uses' gives a specific verb and resource, and the enum of seven apps bounds the scope precisely. It also names the sibling connection_status as the way to inspect state, so the agent can separate the two tools without opening a 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?

It states the alternative explicitly ('To see which apps are connected, call connection_status') and gives a hard behavioral rule ('Never ask the user for a key in the chat'). What is missing is an explicit when-not-to-call (e.g. what happens if the app is already connected, or whether re-connecting is safe).

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