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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive, closed-world); the description goes well beyond by disclosing the entitlement model, the exact truncation behavior without a paid plan (first 5 rows plus locked.count/locked.by_type), and the fields permanently withheld (contact values, decision-maker names). It also explains that DATA_QUALITY rows are excluded unless requested. This is unusually rich behavioral disclosure.

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?

The content is largely front-loaded and purposeful, but it is delivered as one dense run-on passage mixing definition, family taxonomy, access rules and a promotional plan URL. The marketing sentence ('7 days free at https://...') and the sheer density reduce scannability for an agent trying to extract the call-relevant facts.

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, so the description must explain returns, and it does: it enumerates the per-anomaly fields (metric, current/prior value, peer median, percentile, robust deviations, filing date, trigger sentence, confidence, severity). It also covers the locked/entitlement shape of every answer, leaving nothing essential for calling the tool correctly.

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 schema description coverage at only 36%, the description has to carry weight, and it does: it maps user intent onto family, anomaly_type, firm_class ('class'), state, severity, min_raum_usd ('minimum RAUM'), firm_crd and date, and explains what the family enum values mean. It does not cover the limit cap of 25 or the meaning of the sort options, which are left to 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?

It states a specific verb and resource (surfacing reported values and filing-to-filing changes that deviate from a peer group), names the peer-group composition rule (RAUM band, 30+ advisers), and enumerates the four anomaly families. This clearly distinguishes it from siblings like search_ria_changes and changes_since, which lack the peer-relative, outlier framing.

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?

It gives strong operating context ('a place to look, never a conclusion; there is no master score') and lists the filterable dimensions (family, anomaly_type, class, state, severity, minimum RAUM, CRD, date). What it lacks is explicit routing to sibling tools for non-peer-relative change queries, so an agent gets clear context but no stated alternatives/exclusions.

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