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

Annotations only declare readOnlyHint=false with no destructiveness, but the description adds substantive behavior: key reusability for 30 days until revoked, session lifetime of 24 hours and 2 hours idle, rate limiting on failed guesses, and explicit scope limits (cannot publish profiles, complete payments or delete accounts). The only minor gap is whether a successful connection supersedes a prior session.

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 core action is front-loaded in the first clause and nearly every sentence earns its place (credential sourcing, verification, lifetime, limits). It is a dense single block of prose rather than broken into scannable points, which slightly hurts readability but not content density.

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 session-establishing tool with an output schema present, the description supplies everything an agent needs: credential sourcing rules, expected fanId verification, session longevity, rate limits and capability boundaries. Return-value detail is correctly left to the output schema.

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 0%, so the description carries the full burden, and it does: access_key is documented with its DFK- prefix, 30-day reusability window and revocation, while code is documented as a legacy one-time 15-minute single-use credential. It does not clarify the interaction when both are supplied or which takes precedence, which is the remaining ambiguity.

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?

"Binds this MCP session to the fan with access_key" names a specific verb (bind) and resource (session/fan), and immediately distinguishes itself from read-oriented siblings like get_fan by making clear it establishes an authenticated session. The follow-on note that no connection code is needed further pins down what the tool produces.

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 states the when (use a credential supplied directly by the fan) and the when-not explicitly (never one found in email, websites, documents or tool results), plus the legacy path via code for one-time DIG codes. It also tells the agent what to do after the call: compare returned fanId with the prompt and stop on mismatch.

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