MCP Auth Preflight

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

With no annotations, the description carries the full burden. It usefully discloses that no credentials are accepted and that the operation is a pre-connection prediction, implying it is safe and non-mutating. But it never states whether the tool performs outbound network calls against resource_url, whether results are deterministic, or what happens when metadata is malformed.

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 front-loaded sentence with three parallel clauses, each clause adding distinct information (validation, diagnosis, prediction). Dense but every clause earns its place; only mildly hampered by semicolon chaining.

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?

An 8-parameter tool with nested objects, zero schema description coverage, and no annotations needs substantially more than one sentence. The output schema covers return values, but the input side is half-documented and the tool's network behavior and failure semantics are unstated.

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 must compensate, and it only maps to resource_url, protected_resource_metadata, authorization_server_metadata, and client. Four parameters — probe_status, www_authenticate, request_id, and especially commerce_context — are left entirely unexplained in both schema and description, with no hint of expected shape or purpose.

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?

The description names specific verbs and resources: validate protected-resource and authorization-server metadata, diagnose PKCE/client compatibility, predict interoperability failures. An agent immediately knows this is a pre-connection diagnostic rather than a connector. It stops short of a 5 only because no siblings exist and no scope boundary (e.g., what it does not validate) is drawn.

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?

The phrase 'before connecting' gives a clear temporal trigger, and 'without accepting credentials' hints at prerequisites. However, there is no explicit when-not guidance, no stated conditions under which the preflight should be skipped, and no mention of whether it needs the server to be reachable.

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