Take network VPN peer config

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

Adds substantial context beyond the annotations: the one-time pickup semantics and 410 on a second call, the 'mutation despite GET' clarification, that the ciphertext is only decryptable by the customer's external key and the tool never handles private keys, required networking:read/manage scopes, backend ownership/2FA enforcement, and pending-operation/polling semantics. This is exactly the kind of disclosure annotations cannot carry.

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?

Purpose is front-loaded, but the paragraph then packs in scope, key handling, auth, pending-operation polling, and retry policy into a dense run of sentences. All of it is useful, but it is verbose and could be tightened into structured lines without losing meaning.

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 destructive, non-idempotent one-time-pickup mutation with no output schema, the description covers the one-shot nature, failure outcome (410), scope requirements, mutation semantics, and how to interpret pending/in_progress vs failure. An agent has everything needed to invoke it safely.

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?

The two UUID parameters are documented in the schema and the constraints are self-evident. The acknowledge_one_time_pickup constant param has no schema description; the description only indirectly implies it via the 'ONCE'/'second pickup is 410' wording, which is enough to convey its meaning but not explicit.

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 and resource ('Consume a device's or site's sealed configuration ONCE, including sealed IPsec site material'), which is far more precise than the title. It doesn't explicitly name a sibling alternative (e.g., get_network_vpn_peer_recipe) for differentiation, so it stops short of a 5.

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?

Gives clear preconditions ('Read current capabilities and owned resource state first; obtain approval for the exact change') and post-use instructions ('Save and decrypt the returned sealed payload outside MCP'). It does not contrast with sibling tools for related reads, but the when-to-use context is solid.

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