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

Beyond the annotations, it discloses partial-update semantics ('Only fields supplied are changed'), that an empty URL disconnects, that the API key can be cleared, and that an account-scoped MCP agent token is required. One caution: annotations set destructiveHint=false, yet disconnecting/clearing credentials removes existing configuration, so an agent gets no warning that this is irreversible — though that is an omission rather than a contradiction.

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 action set is front-loaded in the first clause, followed by prerequisites and cross-tool routing. Sentences are dense with no filler, though the embedded supplier-spec list makes the opening block slightly heavy to parse.

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 four-parameter mutation tool with full schema coverage, no output schema and clear mutating annotations, the description supplies the prerequisites (server contract, https, token scope) and the partial-update rule that an agent needs to call it safely. What is missing is any statement of what happens to bookings or availability when a connection is swapped or removed.

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 every parameter is already documented, including the empty-string clearing semantics for mcpServerUrl and mcpApiKey. The description restates the disconnect behaviour and adds the token-scoping prerequisite but does not explain pricesByDay beyond what the schema says. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Description uses specific verbs (connect, change, disconnect) against a specific resource (a Stay's link to the partner's own MCP server) and names the sibling that handles the adjacent job ('Set each room's mcpRoomId with updateStayRoom'). An agent can distinguish it from getStaySupplierConnection and updateStayRoom without opening a schema.

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 concrete operating conditions: the partner server must implement get_allocation, check_availability, create_booking and cancel_booking, and must be public https. Disconnect is routed via an empty mcpServerUrl, and room-level IDs are delegated to updateStayRoom. Minor gap: it never says to read state first with getStaySupplierConnection, though that is strongly implied.

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