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

Annotations only declare non-read-only, non-destructive, closed-world; the description goes far beyond by disclosing what pairing returns (a resumeKey), that resuming from a second MCP session attaches additively rather than replacing, that the tab's WebMCP tools get injected into the tool list, and that ChatGPT-style clients lose pairing between calls.

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 in the first sentence, then the fallback paths. Six sentences is on the long side and the ChatGPT-specific aside is dense, but each sentence conveys distinct operational information rather than 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?

Covers setup, return value (resumeKey), multi-session semantics, post-pairing tool discovery, and the degraded-client workaround, even though there is no output schema to lean on. An agent has enough to pair, recover, and keep calling correctly.

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%, so both parameters are already documented; the description still adds lifecycle meaning — the code is user-visible in the studio header, and resumeKey comes from a prior result and must be threaded through every genmc_call/genmc_status in session-per-call clients. It does not state that either parameter alone suffices, leaving the either/or relationship to inference.

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 to the user's open genMC studio tab.' It immediately explains the two ways in (new code vs. resumeKey), which distinguishes pairing from the sibling genmc_call/genmc_status operations it later references.

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?

Explicit routing: use the code after the user picks 'Connect agent'; use resumeKey when the MCP connection drops or restarts; use genmc_status/genmc_call if the tool list does not refresh. Alternatives and their triggering conditions are named, not implied.

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