detect_change_points

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

No annotations are supplied, so the description bears the full disclosure burden, and it does describe the mechanism and threshold behavior ('flags changes exceeding sensitivity * MAD'), which tells the agent the output is threshold-sensitive. It does not state that the operation is non-mutating, whether it is deterministic, or any cost/performance characteristics. An output schema exists, so return-shape detail is fairly excused, but the read-only and side-effect profile is left to inference.

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?

Three short sentences, front-loaded with the primary action and followed by the mechanism, with no redundant restatement of the name. Slightly compact to the point that the interval parameter and threshold formula could use one clarifying clause, but nothing is wasted.

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 moderately complex analytical tool with a nested object parameter, no annotations, and an output schema, the definition covers the algorithm well but omits the meaning of 'interval', the expected serialization of the nested series, and any pointer to sibling tools. Enough to call it plausibly, not enough to call it confidently.

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?

With 0% schema coverage, the description must carry the load. It does explain the two most semantically opaque knobs: 'sensitivity' is the multiplier on the median absolute deviation threshold, and 'window_size' is the early/late window length used in the mean comparison. It gives no meaning for 'interval' (presumably the time bucket granularity) and does not describe the nested series structure beyond the phrase 'per-event-type time series', leaving half the parameters under-specified.

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 and resource ('Detect change points') and even specifies the algorithm (sliding window mean comparison, MAD threshold), so an agent knows exactly what the tool computes. It never distinguishes itself from temporal siblings such as detect_temporal_outliers, aggregate_temporal_events, or check_temporal_persistence, leaving the family boundaries implicit.

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 clause 'Works on per-event-type time series' implies an applicability constraint, telling the agent the input shape required. There is no explicit guidance on when to prefer this over the temporal-outlier or aggregation siblings, and no stated prerequisites or exclusions.

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