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

Goes well past the readOnly/idempotent annotations by disclosing the entitlement model in detail: free-tier lists return only 5 full rows plus locked counts, records expose subject plus 3 related names, contact values and decision-maker names are withheld as types/counts, and every response reports withholding via `entitlement` and `locked`. Ordering/windowing semantics are also stated.

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-loads the purpose and event taxonomy, then the filters, then the access model, which is a sensible order. It is dense and the trailing pricing CTA/URL is promotional, but the access paragraph carries genuine operational information rather than filler.

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 10-parameter, no-output-schema, entitlement-gated search tool, the description covers the two riskiest unknowns: what gets withheld and how results are ordered/windowed. Missing event_type/domain value hints and per-parameter semantics for signal_family and the integer thresholds keeps it short of 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?

With only 30% schema coverage across 10 parameters, the description partially compensates by naming domain, dfx_id, event_type, state, significance and window as filters, and by explaining the default exclude_routine behavior. It leaves signal_family, limit, within_days (only as 'window'), and min_significance thresholds unexplained, and does not clarify valid event_type or domain values.

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 resource (dated change events) and enumerates the concrete event types it covers across named domains, so an agent can tell it is a broad cross-domain activity tape rather than a single-entity lookup. It does not, however, distinguish itself from near-siblings such as changes_since, search_signals, or search_capital_changes.

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?

Offers implied usage guidance: filter by domain/subject/event_type/state/significance/window, and a default exclusion of routine 13F and fund-reporting noise 'unless asked for.' But it never states when to prefer this tool over the many overlapping search_*_changes and signals tools, and gives no prerequisites for the dfx_id subject form.

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