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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: it explains that anomalies are 'a place to look, never a conclusion', that data quality rows are kept apart, that book size and revenue are never estimated, and that each derived metric comes with its formula. It also discloses the source, date, and rights class for contact data. This is substantial behavioral transparency, though it doesn't describe pagination or output size limits, which would be the only remaining gap.

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 information-dense and front-loaded with the core purpose, but it is a single very long sentence (over 150 words) that packs many items into a comma-separated list. It is not poorly structured, but it would benefit from breaking the content into a short summary sentence followed by a bulleted list of what is included. Every item earns its place, but the lack of visual structure makes it harder for an agent to parse quickly.

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 read-only, single-parameter tool with no output schema, the description is remarkably complete: it enumerates the full set of returned content categories, explains the derivation of metrics, flags data quality handling, and specifies input formats. The only missing context is the output shape (e.g., whether results are returned as a single object or a nested structure) and any pagination behavior, but with no output schema and a single id input, the description covers nearly everything an agent needs to invoke it correctly.

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 100%, so the schema already documents the single parameter dfx_id with its format and examples. The description adds value by explaining that the id can be either a dfx:ria:<uuid> or a CRD number as a string, and by naming the source tools (search_ria, resolve_name, search_entities) that produce valid ids. This goes beyond the schema's basic type/description, though the schema itself is already quite clear, so a 4 is appropriate rather than a 5.

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 opens with a clear, specific verb phrase ('What a practice looks like from what it filed') and enumerates the exact resource: one adviser's practice profile built from Form ADV fields, derived metrics, archetypes, peer group, anomalies, offices, retention, and public contact path. It distinguishes itself from siblings like get_ria_firm, get_ria_advisor, and search_ria_practices by focusing on the single-practice profile with derived analytics and anomalies. The title reinforces the scope, and the description's specificity leaves no ambiguity about what the tool returns.

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 states the input format explicitly ('Accepts a dfx:ria: id or a CRD') and names the source tools for obtaining that id ('from search_ria, resolve_name or search_entities'). It also clarifies what the tool is not for: it is a single-practice profile, not a search or a list tool, and it explicitly says advisor book size and revenue are marked UNKNOWN and never estimated, which prevents misuse. However, it does not explicitly name sibling alternatives or state when to prefer get_ria_firm vs get_ria_practice, so it falls just short of a 5.

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