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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description only needed to add context, and it does: data is embedded curated static reference, no API key required, and it is sourced from the annual Kitces survey for 2023–2024. That vintage disclosure is genuinely useful for an agent judging freshness, though it doesn't say whether the data is aggregated medians only or also per-firm segments.

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-loaded with the core verb and scope, then a scannable bulleted category breakdown, then source and access notes. The category list is long for a single-parameter tool and restates the default ('all') that the schema already declares, but each bullet is informative 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?

With an output schema present and rich annotations, the description needn't explain return values, and it covers source, vintage, and category coverage adequately. The remaining gap is that it never clarifies that the extra query-style parameters (wholesaler_ids, additional_display_fields, exclude_fillers) are likely irrelevant to this static reference dataset, which could mislead an agent into passing them.

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?

The description adds real meaning to the `category` parameter by mapping each value to the metrics it contains (e.g., 'technology: software adoption rates and tech spend'), which the schema's option list alone does not convey. It does not address the other nested params (wholesaler_ids, source_resource_id, exclude_fillers), which appear to be generic plumbing inherited from a query schema and whose relevance to static benchmark data is left unexplained.

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 verb and resource ('Return Kitces Research advisor practice benchmark data') and enumerates the five content categories, so an agent knows exactly what comes back. Nothing in the sibling list (13F holdings, fund profiles, IAPD/LEI/BrokerCheck lookups) overlaps with this resource, making the tool trivially distinguishable.

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 only implied: it notes that category='all' (default) retrieves everything, which hints at a broad-vs-narrow choice. There is no explicit statement of when to reach for this tool versus another, nor any when-not guidance or prerequisite (e.g., that it is unsuitable for firm-specific rather than industry-wide comparisons).

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