instance_update

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

Adds real behavior beyond the annotations: the write is persisted to the database yet only applied later by the scheduler, and the tool cannot confirm the change is live. That async propagation caveat is exactly the kind of context annotations cannot express. It stops short of 5 because destructiveHint=true is left unqualified – no word on whether re-pointing ports/server_name breaks a running instance or whether the change is reversible.

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, no waste, ordered by importance: what it does, the alternative, then the operational caveat. 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?

For a 7-parameter mutation with no output schema, the description covers the essentials an agent needs to call it safely: partial-update semantics and the fact that success is not immediately verifiable. Missing only permission/error expectations and any hint that the instance must already be registered, which the hostname description partially covers.

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 100% and each property already carries an "omit to keep" description, so the description's patch-semantics line mostly restates what the schema documents. It adds no field-level meaning (e.g. what hostname keys on, or how port vs https_port interact), so baseline 3 applies.

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 ("Change a registered instance") and immediately distinguishes it from the sibling creator ("Use instance_create for a new host"). An agent can tell update apart from create/delete/get without opening any schema.

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?

Explicitly routes new-host work to instance_create, and the patch semantics ("omitted fields keep their value") tell the agent it may send a partial payload. It gives no when-not guidance (e.g. use instance_get first to inspect current values, or that hostname must already exist), keeping it short of a 5.

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