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

With no annotations, the description carries the burden. It usefully discloses that this hits a 'real upstream' despite being a dry run, which flags real network side effects. However it says nothing about auth requirements, whether anything is persisted, or what the dry run returns.

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 compact sentence, front-loaded with the action and followed by the alternative. Zero filler; every clause earns its place.

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?

The tool has nested object params and no output schema, so the description should explain the return of a dry run and the execution/auth model. Instead it covers only the action line and an alternative pointer, leaving the agent under-informed for a network-touching test tool.

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 100% and the schema richly documents all three parameters, including the tenant_key auth precedence rule. The description adds no parameter-level meaning beyond what the schema already provides, so this is the baseline 3.

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States a specific verb (dry-run) and resource (an unpublished http spec) plus the target (its real upstream). It carves out scope against siblings by deferring 'the other cases' to host.quickstart, so an agent can orient quickly. It stops short of naming exactly which sibling cases are excluded.

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 implies usage via 'unpublished http spec' and routes non-matching cases to host.quickstart, which is useful. But 'the other cases' is not spelled out, so the agent must infer whether an already-published spec, a non-http spec, or a plain tool test belongs elsewhere.

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