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

No annotations are provided, so the description carries the full burden. It reveals that no review step occurs, but says nothing about what the packet contains, whether a durable record is created, who can see it, or what the mandatory acknowledge_manual_forwarding acknowledgement actually commits the caller to.

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?

Three short sentences with no padding, and the resource is front-loaded. However, the second and third sentences convey only discouragement rather than operational guidance, so the length is efficient but the content is not load-bearing.

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?

A mutation tool with zero annotations, no output schema, and no parameter description coverage should be doing much more work in prose. An agent finishes reading without knowing the side effects, the packet's lifetime given maximum_uses=5, or why a manual-forwarding acknowledgement is forced.

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 and it adds nothing about any of the three parameters. idempotency_key, the const-5 maximum_uses, and the required acknowledge_manual_forwarding=true are left entirely to raw schema constraints with no narrative meaning.

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?

"Legacy optional peer-referral packet creation" names a resource and an action, but "legacy optional" undercuts it and the description never explains what a referral packet is or what creating one accomplishes. It does not distinguish this from siblings such as discover_agents or discover_external_agents, which look like the actual acquisition path it alludes to.

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 a when-not ("not part of the canonical acquisition path", "no referral review is required for ordinary AION utility", "Machine-first discovery remains preferred") but never states a positive when-to-use or names the alternative tool an agent should pick instead. The steer toward machine-first discovery is directional but not actionable.

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