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

Goes well beyond the readOnly/idempotent annotations by disclosing the entitlement model: unentitled lists return 5 rows plus locked.count/locked.by_type, records expose only subject and first 3 related names, and contact values/decision-maker names are withheld with types and counts. It also specifies keyset ordering by event occurrence and that withholding is echoed in `entitlement` and `locked`.

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?

Dense but front-loaded: purpose and event taxonomy come first, then filters, then ordering, then access constraints and the pagination example. The closing promotional plan pitch ('7 days free at...') is the one element that doesn't earn its place in a tool definition.

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 12-parameter, no-output-schema search tool with a non-trivial paywall, it covers the critical behaviors: return shape under entitlement, pagination via cursor, and historical window reads. A few parameters (limit, within_days, signal_family) and the concrete response envelope remain undocumented.

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 42% schema coverage, the description compensates by explaining the semantics of since/until (event occurrence, full history, keyset paging with a year example), dfx_id as subject, and exclude_routine's default behavior. It leaves limit, within_days, and signal_family unaddressed, so the compensation is strong but incomplete.

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?

Names a concrete resource (dated events across named domains) and enumerates the event types it covers, so the agent knows exactly what it returns. It does not, however, explicitly distinguish itself from close siblings like changes_since or search_signals, leaving that boundary to inference.

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?

Gives concrete guidance on filtering (domain, dfx_id, event_type, state, significance, window), states that routine 13F/fund-reporting noise is excluded unless asked for, and provides a worked example (firm's 2005 deals via dfx_id + since/until). Missing an explicit 'use X instead when...' routing against sibling tools.

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