connect

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

Annotations only declare readOnlyHint=false and openWorldHint=false, so the description carries most of the behavioral load. It discloses meaningful traits: key-apps explain where to obtain a key and the terminal command that stores it, Google's flow starts a browser sign-in and returns immediately so the next call works, and the agent must not request keys in chat. Auth/permission nuances beyond this aren't covered.

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 purpose followed by compact per-case behavior and a memorable closing rule; every sentence contributes. It is slightly dense/multi-clause in the middle but avoids redundancy with the schema.

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 and minimal annotations, the description covers the critical decisions: how different app types behave, the immediate return on Google sign-in, how to check status, and the key-handling safety rule. Return shape is left implicit but is not required here.

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% with a single enum parameter, setting baseline 3. The description adds real semantic value by branching the 'app' values into behavioral categories (key-issuing apps vs Google), which tells the agent what a given enum value will trigger beyond the schema's flat 'The app to connect.'

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?

The opening sentence gives a clear verb (Connect) and resource (one app this server uses), and the body differentiates this tool from the sibling connection_status by routing status checks there. The scope is specific enough that an agent can pick it without opening the schema, though the declarative 'what it does' could be sharper.

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 gives explicit per-app conditions (key-issuing apps vs Google) and names the alternative tool (`connection_status`) for seeing which apps are connected. It also gives a hard usage rule: never ask for a key in chat. It stops short of stating when not to use the tool beyond the one routing example.

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