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

Annotations already communicate read-only, idempotent, and non-destructive behavior, so the description only needs to add context. It usefully adds that results are "Ordered and windowed by when events occurred" and that "Routine 13F position and fund-reporting noise is excluded unless asked for," which clarifies how the exclude_routine filter behaves.

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 description is one dense sentence but front-loads the core identity and uses the long list of event types to convey real scope. Every clause adds information; it is slightly list-like but not padded. It earns a high score because the detail replaces the missing output schema context.

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 and 10 parameters, so the description carries a heavy burden. It provides a solid orientation and covers most filter dimensions, but it omits value formats, event_type enumerations, output shape, and pagination behavior. It is adequate for initial selection but not fully complete for nuanced invocation.

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 only 30%, so the description must compensate. It does map several parameters semantically — "domain, subject dfx_id, event_type, state, significance and window" — and the event-type list gives meaning to event_type. However, signal_family is never explained, and min_significance and window are only hinted at rather than precisely defined.

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 states a specific resource: "Dated events across family offices, sponsors, venture, private equity and real estate" and enumerates concrete event types. It distinguishes itself from the many domain-specific sibling change tools by emphasizing the cross-domain "change tape" scope and by noting the ability to filter by domain.

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 description implies broad usage: this is the general cross-domain event search, and it says "Filter by domain, subject dfx_id, event_type, state, significance and window." However, it never tells an agent when to prefer this over domain-specific siblings like search_private_credit_changes or search_capital_changes, and it offers no explicit when-not-to-use guidance.

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