get_meta_anomaly_signal

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

No annotations are provided, so the description carries the full burden. It discloses the algorithm (rolling-baseline Z-score), the per-campaign-metric evaluation scope, severity banding (severe/moderate/mild based on multiples of threshold), direction (spike vs drop), and output ordering (severity → recency → |z|). It does not state auth requirements, rate limits, or computational cost, but the behavioral disclosure is unusually rich for an analysis tool.

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 purpose and carries dense technical detail in a few sentences. Every sentence contributes to understanding the algorithm or usage. Slightly long but justified by the complexity of the detection model; no obvious padding.

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 an analysis tool with 8 parameters, 100% schema coverage, no output schema, and no annotations, the description supplies the algorithmic context an agent needs to interpret results (what a flag means, severity levels, sorting). It does not describe the return format (list of anomalies with fields), which would help, but the core call-time context is complete.

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 the schema already documents all 8 parameters with defaults, ranges, and formats. The description adds semantic meaning by explaining what baseline_days and z_threshold do in the algorithm (trailing days vs prior baseline, flagging threshold), which is helpful context beyond the schema's terse descriptions. Baseline 3 is appropriate when the schema does the heavy lifting.

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+resource ('Detects daily anomalies in Meta campaign performance') and immediately distinguishes itself from the closest sibling by referencing Meta's MCP ads_insights_anomaly_signal and clarifying it is computed locally. An agent can differentiate this from get_meta_campaign_performance and get_tiktok_anomaly_signal without opening schemas.

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 states the use case at the end: 'Use to triage something changed yesterday before doing a full audit.' It also names the equivalent MCP tool, effectively routing the agent between local and remote anomaly detection. When-to-use is clear; when-not-to-use is implied by 'before doing a full audit.'

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