get_device_parameter_snapshot

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered. The description contributes genuinely new behavioral context that the annotations cannot express: the returned values are frozen at backup time and may not reflect the device's current state — a critical caveat that prevents misinterpretation of results. It also mentions paginated retrieval, though it does not describe page size limits or ordering.

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 compact sentence with zero filler, front-loading the core action and then the key caveat. Nothing is redundant, though it is arguably too terse given the undocumented parameters.

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 return shape need not be described, and the staleness caveat covers the main interpretive risk. But for a 4-parameter tool with 0% schema coverage, the group filter and pagination semantics are left entirely unexplained, which is a real gap for correct invocation.

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% across 4 parameters, so the description must carry the burden and largely fails to. "分页" loosely implies limit/offset, but neither is explained (defaults 50/0, max bounds, ordering), and snapshot_id and the group filter receive no mention at all. An agent must guess how group scoping interacts with pagination.

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 (分页查看/paginated view) and resource (已有实机备份 = an existing device backup), and enumerates the content returned: definitions, raw values, and precise engineering values. That is more than a restatement of the name. It does not explicitly differentiate itself from near-siblings such as list_device_parameter_snapshots or compare_device_parameter_snapshots, which keeps it out of the 5 tier.

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?

"这是备份时读数，不是当前值" implies the selection condition: use this when you want historical snapshot data rather than live device readings (read_device_parameters / probe_device_read_only). However, no alternative tool is named and no exclusion or prerequisite is stated, so the routing is left to inference.

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