Idm Get History

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

No annotations are provided, so the description carries the full burden and does meaningful work: it discloses gateway-side aggregation, that inactive devices still have records ('the gateway keeps their records'), that average intervals are in SECONDS, and that average mode adds 'n' and 'sd' to each returned point. It says nothing about permissions, result-size limits, or error behavior.

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?

Front-loaded with the core action, then a compact mode list with aligned labels — efficient and scannable. Minor cost: identifiers like `m` in the scale line are never defined in the prose, so the reader has to infer what a returned point contains.

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 values need not be documented, yet the description helpfully hints at the extra `n`/`sd` fields in average mode. Combined with mode selection, units, defaults, and inactive-device support, an agent has enough to call it correctly for a 9-parameter, 4-mode tool; only error and permission behavior are absent.

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 already 100%, so the baseline is 3. The description goes beyond it by defining the mode combinations that tie parameters together (average requires scale; calc collapses the whole record set) and by clarifying the unit of `average`. It adds cross-parameter semantics rather than just restating individual fields.

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: 'Read recorded samples of one parameter, aggregated by the gateway.' The four-mode framing (regular/scale/average/calc) makes it unmistakably the historical-samples tool rather than a live-value sibling like idm_get_value or a stream reader like idm_read_stream.

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 tells the agent how to select behavior: 'Four modes, chosen by which arguments are set,' with each mode's argument combination spelled out (scale → average, calc → single aggregate). It also notes the inactive-device case. No sibling alternatives or when-not conditions are given, so it stops short of 5.

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