tvh_snapshot

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

The annotations already declare read-only, idempotent, non-destructive, and open-world behavior. The description adds important behavioral limits beyond the annotations: it cannot recreate deleted nodes, recordings, or hardware, and it excludes secrets and write-once fields.

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 short and front-loaded: the export purpose comes first, followed by local-save guidance and then critical limitations. Every sentence adds useful information without repetition.

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?

An output schema exists, so the description does not need to explain return structure. It covers the key export semantics and limitations well, though it leaves the required uuids parameter under-specified.

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 schema has one required parameter, uuids, with 0% description coverage. The description only mentions 'selected objects' and does not explain that the selection is by UUID array or how those UUIDs should be obtained, so it does not compensate for the schema gap.

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 uses a specific verb and resource: export selected objects' writable/readable fields as a JSON change snapshot. It clearly identifies the output artifact and distinguishes itself from a complete backup, so an agent can tell what this tool produces.

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 gives clear usage context: save the returned JSON locally and do not treat it as a complete Tvheadend backup. It also states what cannot be recovered, but it does not explicitly compare against siblings such as tvh_restore_snapshot, tvh_get_node, or tvh_api_read.

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