connect_chatgpt

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

With no annotations, the description carries the full burden. It does disclose that this mutates an external account (creates or repairs a connector), which is useful, but it says nothing about authentication requirements, whether a browser flow or ChatGPT login is needed, idempotency of the 'repair' path, or what happens on failure — and the truncation likely removed exactly that content.

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?

The content present is front-loaded and efficient, but the description terminates mid-sentence at 'so...', which is a structural defect rather than concision. An agent receives an incomplete claim about side effects.

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 zero-parameter tool that writes into a third-party account with no annotations and no output schema, the description should cover prerequisites, auth flow, and the result of the operation. Instead it stops mid-thought, so an agent cannot tell what a successful call produces or what the user must do beforehand.

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?

The input schema declares zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly implies the tool needs no arguments since the target Mac and ChatGPT account are implicit.

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 concrete verb and resource: connects this Mac to ChatGPT by creating or repairing an LMCP connector inside the user's ChatGPT account. That is much more specific than a bare 'connect' and implicitly distinguishes it from diagnostics/state siblings like lmcp_state or lmcp_doctor. However, the sentence is cut off mid-clause ('so...'), so the full scope of what it does is not delivered.

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?

There is no indication of when to call this versus alternatives (e.g. lmcp_state, lmcp_upgrade_diagnostics, lmcp_doctor) or what preconditions must hold. The truncated trailing clause suggests guidance was intended but it never arrives, leaving the agent to guess.

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