vm_pin

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

With no annotations at all, the description carries the full burden, and it does disclose the core behavioral effect: the item is moved/preserved outside a temporary cache, implying it survives disconnect-driven eviction. It says nothing about permanence, whether repeated pinning is idempotent, whether pinning requires ownership of the thread, or what a failed pin looks like, leaving significant behavioral gaps for a state-changing tool.

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 tight sentence with the preservation goal front-loaded and the timing constraint ('before disconnecting') placed at the end where it reads as a precondition. No filler or redundancy; it is simply too short to cover more.

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?

This is a state-changing tool with no annotations, no output schema, and three fully undocumented required parameters, so the description is the only source of truth and it addresses only the high-level intent. It omits permanence/lifetime of a pin, the relationship to vm_disconnect and the cache, failure modes, and any indication of what the call returns.

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% and all three parameters (session, capture_id, owner_thread_id) are required but undocumented. The description obliquely hints that an image/capture is the target, which weakly covers capture_id, but session and especially owner_thread_id get no explanation at all — including whether owner_thread_id is an authorization constraint or merely bookkeeping.

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 a specific verb ('Preserve') and an object ('report/evidence image') plus a scope ('outside the temporary cache'). However, the object terminology does not map cleanly onto the required 'capture_id' parameter, so an agent cannot be fully certain that 'report/evidence image' and a 'capture' are the same thing, or what kinds of captures are pinnable.

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 disconnecting' implies the correct moment to call it and implicitly references the sibling tool vm_disconnect, which is genuinely useful timing guidance. It stops short of an explicit when/when-not rule (e.g., 'call this instead of relying on vm_disconnect to persist captures'), so the routing remains inferential.

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