Reading history

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

readOnlyHint=true already tells the agent this is a safe read, so the description's job is to add behavior — and it does: it discloses the exact summary fields returned, that series points are averaged per bucket, and the important caveat that partial coverage should be read as 'no data', not 'nothing to report'. It does not mention auth/device prerequisite handling beyond what the schema says, but the return-side transparency is substantial.

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?

Two dense sentences, front-loaded with the resource and the return shape; every clause carries information. The long parenthetical threshold list is verbose but genuinely useful, so it earns its place; a slightly more scannable structure would push this higher.

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?

There is no output schema, yet the description adequately documents the return shape (statistics, timestamps, exceedance minutes, optional series, coverage) and flags the key interpretive pitfall. For a 6-parameter read tool this is nearly complete; small gaps remain around units, pagination/limits, and how metrics default interacts with per-metric results.

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 coverage is 100%, so baseline would be 3; the description earns a 4 by explaining what max_points functionally changes (series vs summary-only, bucketed averaging) and by defining the threshold semantics behind the exceedance counts (CO₂ > 1000/1500 ppm, PM2.5 > 15/35, humidity > 60/70 %). It adds no extra meaning for device, start, end, or hours beyond the schema.

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 states a concrete resource and action — a Qingping sensor's history over a time period — and enumerates the returned statistics (min/max/avg/first/last, timestamps, threshold-exceedance minutes). It clearly implies the historical, over-a-period framing that separates it from qingping_current, but it never names the sibling or explicitly contrasts with it.

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?

Usage is implied rather than stated: 'With max_points > 0, also returns the series ... to draw a chart' hints at the charting use case, and the coverage note warns that empty/partial history means 'no data'. However, there is no explicit when-to-use versus qingping_current, no mention of qingping_alerts for threshold breaches, and no guidance on choosing hours vs start/end.

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