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

Beyond the annotations (readOnlyHint, idempotent, non-destructive, closed-world), the description discloses substantial behavior: without a paid plan a list returns only the first 5 rows plus locked.count/locked.by_type, records expose subject plus 3 related names per section, and contact values and decision-maker names are never returned. It also states that every answer surfaces what was withheld via `entitlement` and `locked`, which is exactly the kind of entitlement/response context an agent needs.

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 purpose is front-loaded and the ACCESS block is well organized, but the description reprints all 19 archetype enum values that already exist verbatim in the schema, which is pure duplication. The result is a dense single block whose length is partly unearned. Structure is sensible (purpose -> metrics -> access) but not tight.

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 20-parameter screening tool with no output schema, the description covers a lot: what can be filtered, how results are sorted, and the shape of what comes back under both free and paid tiers. It stops short of describing record-level fields, but the entitlement/locked contract is clear enough for correct invocation and interpretation.

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 10% schema description coverage across 20 parameters, the description must carry the load, and it largely does: it maps categories to filters (archetype, class, RAUM band, advisors, growth, private funds, shares, and named flags such as PE owner on Schedule A, custody, wrap, performance fees, pension consulting, financial planning). It also constrains meaning ('no book size, no revenue') and notes each metric is filed-field derived. A few params (cursor, limit, min_hnw_of_private, min_private_funds) get no added detail.

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 verb and resource ('SEC-registered advisers screened on the practice layer') and enumerates the exact screening dimensions (archetype, class, RAUM band, advisors, growth, flags), making its scope unambiguous. It references the sibling get_ria_practice as the place where metric formulas live, giving partial sibling differentiation, though it never explicitly contrasts itself with search_ria or search_ria_teams.

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?

Usage is implied through the enumeration of available screens and the pointer to get_ria_practice for formulas, so an agent can infer the tool is for practice-layer screening. However, there is no explicit when-to-use/when-not guidance against alternatives like search_ria or search_ria_teams. The detailed ACCESS paragraph is behavioral, not selection guidance.

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