gateway_call_tool

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

Annotations contain only a title (no readOnly/destructive hints), so the description carries the full behavioral burden. It adds genuine context by disclosing that calls pass through auth, scope checks, and audit logging — the defining behavioral trait of a gateway proxy. But it omits failure behavior, idempotency semantics, and any distinction from gateway_call_tool_sanitized, making it minimally transparent rather than rich.

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?

A single, tightly-written sentence with zero filler; the verb and resource lead, and the governance qualifiers trail cleanly. It is slightly too sparse to carry the needed operational guidance, but that is a completeness issue rather than a conciseness defect.

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 generic pass-through tool with 0% schema coverage and no behavioral annotations, one sentence is insufficient. Missing are parameter semantics, how an agent discovers valid route/tool_name values, idempotency behavior, and the relationship with gateway_call_tool_sanitized. The output schema covers return values, but invocation decisions remain under-informed.

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 description coverage is 0%, so the description must compensate, yet it explicitly explains no parameter. 'Private backend route' loosely reinforces that tool_name maps to a Route (consistent with the x-mcp-header hint), while arguments_json and idempotency_key remain undocumented in both the schema and the description.

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 ('Call') and resource ('private backend route through GatewayMCP') and adds a distinctive governance qualifier (auth, scope checks, audit), which separates this generic dispatcher from the many domain-specific gateway_* siblings. However, it does not differentiate from its closest sibling, gateway_call_tool_sanitized, and the phrase 'backend route' sits slightly awkwardly against the parameter name tool_name.

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?

No explicit guidance on when to use this tool versus the large sibling set, and no mention of the most relevant alternative, gateway_call_tool_sanitized. The word 'private' weakly implies it is for routes not exposed by dedicated sibling tools, but the selection rule is left entirely to inference.

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