connect

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

Annotations only flag it as non-read-only and closed-world; the description adds real behavior: the Google path is asynchronous ('returns at once', approval happens in the browser, next call works), key-issuing apps need an out-of-band key stored via a terminal command, and it issues the guardrail 'Never ask the user for a key in the chat.' That is substantial context beyond the annotations.

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 conditional behavior, then the sibling pointer and the guardrail. Every sentence carries distinct information; nothing is redundant filler.

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 connect tool with no output schema, it covers the required prerequisites, the asynchronous return behavior for Google, and the follow-up verification path via `connection_status`. Nothing needed to invoke it 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% but the schema itself only says 'The app to connect' for a 6-value enum. The description adds per-value semantics by distinguishing key-issuing apps (stripe/linear/github/etc.) from Google's OAuth flow, which materially changes what happens after the call.

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 ('Connect one app this server uses') and immediately differentiates itself from the sibling `connection_status`, which is a status-read rather than a connect action. An agent can tell its function apart from the many *_create siblings 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?

It explicitly routes the 'which apps are connected' intent to `connection_status` and gives distinct usage flows for key-issuing apps vs Google (own OAuth client must be set first). It does not state explicit when-not conditions beyond that, so it falls just short of the top band.

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