detect_temporal_outliers

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

With no annotations, the description must carry the full behavioral burden, and it partially does: it discloses that two statistical methods exist ('IQR' or 'zscore') and that results are per-event-type outlier flags plus statistics. It does not state that the operation is read-only/non-mutating, whether it has computational cost limits on large series, or how the z_threshold interacts with the 'zscore' method.

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, front-loaded sentences: what it does, the method choices, and what comes back. No filler, though the method enumeration could have been folded into the first sentence more tightly.

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 needn't be re-explained, but the most error-prone input — the nested 'series' object and the free-form 'interval' string — is entirely undocumented. For a tool requiring a nested payload structure, the description leaves too much for the caller to guess.

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 including a nested object, so the description needs to compensate and largely fails. It explains the 'method' options but says nothing about the shape of 'series' (event type → buckets → integer counts), the 'interval' format, or the meaning and default of 'z_threshold'.

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 ('outlier detection on event counts') plus the scope ('for a given interval'), which is clearer than a generic 'analyze' label. It implicitly separates itself from temporal siblings like detect_change_points and check_temporal_persistence, but never names them.

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?

No when-to-use or when-not-to-use guidance is offered, and the crowded temporal-analysis sibling set (aggregate_temporal_events, detect_change_points, normalize_temporal_activity, check_temporal_persistence) makes routing ambiguous. The method choice is described, but the decision of choosing this tool over a change-point or persistence check is left entirely to inference.

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