list_cached_images

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

Beyond the annotations (readOnlyHint, idempotentHint, etc.), the description reveals important behavioral traits: it reads a specific local file (~/.vmware-storage/image_registry.json), results may be stale, filtering is performed entirely in memory, and 'truncated is always false' due to that behavior. This adds significant context beyond the structured annotations.

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?

The description is front-loaded with a one-line summary, followed by a clearly separated details section and an 'Args:' block. Every sentence adds value: the staleness caveat, the live-listing alternative, the return envelope explanation, and the parameter semantics. No wasted words.

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 read-only list tool with optional filters and no output schema, the description is complete. It details the return envelope structure ('items', 'returned'/'total'/'truncated'), explains edge cases (empty results, staleness), and covers both parameters. The presence of sibling tools is addressed with the explicit alternative, making the context fully understood.

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 carries the full burden. It explains both parameters: image_type as a case-insensitive file extension filter with examples ('ova', 'iso', 'ovf', 'vmdk'), and datastore as an exact name filter. It also clarifies that omitting either parameter returns all types/datastores, which is not obvious from the schema alone.

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 opens with '[READ] List deployable images (OVA/OVF/ISO/VMDK) from the local cache registry' — a specific verb, resource, and scope. It also distinguishes from the sibling tool scan_datastore_images by stating 'instant, no vCenter connection or datastore I/O' and later recommending the sibling for live listings.

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 description explicitly states when to use this tool ('instant', cached registry) and provides a direct alternative: 'For a live listing use scan_datastore_images instead.' It also notes that results 'may be stale or empty if no scan has run,' setting accurate expectations for cached data.

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