connect

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

Annotations declare readOnlyHint=false and openWorldHint=false, and the description adds meaningfully beyond that: for Google it discloses a non-blocking flow ("starts the browser sign-in and returns at once") and that "the next call works" after in-browser approval, which is critical for an agent not to retry prematurely. It does not cover failure modes or what happens when a credential is revoked, keeping it at a 4.

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?

Four compact sentences, front-loaded with the core action before the app-specific branches and the alternative tool. Slightly marred by awkward phrasing ("says where to get one and the terminal command that stores it") whose subject is unclear, but there is little waste.

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?

There is no output schema, so the description carries the return-behavior burden and does so by describing what comes back for key-based apps (where to get a key, the storage command) and the immediate return for Google. Auth prerequisites for Google ("once the user's own OAuth client is set") are mentioned, though not fully expanded.

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 `app` parameter already carries an enum of all valid values. The description only loosely groups these values ("an app that issues keys" vs "Google"), adding marginal semantics beyond the schema, so the baseline 3 applies.

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 ("Connect") and a bounded resource ("one app this server uses"), and the enum-backed app parameter makes the scope unambiguous. It is clearly distinct from the read-only sibling `connection_status`, which it names.

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 routes the agent: use `connection_status` to inspect what is connected, use this tool to connect one app. It adds two conditional branches (key-issuing apps vs Google OAuth) and a guardrail ("Never ask the user for a key in the chat"). When/when-not is fully covered.

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