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

Annotations cover safety (readOnly, non-destructive, openWorld), and the description adds substantial context beyond them: it is a CURRENT-ROSTER monthly snapshot not an event history, a stale snapshot_month means deregistration, ERA AUM is null by construction, and a disciplinary FLAG is a disclosure not a verdict. This is exactly the kind of behavioral disclosure the structured fields cannot carry.

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?

Long but front-loaded and information-dense, with the core purpose in the first sentence and caveats after. Some redundancy exists (firm_type registered/ERA AUM semantics are stated in both the schema description and the prose), which slightly dilutes conciseness.

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 an 11-param dataset tool with no output schema, the description is complete: it enumerates returned fields (AUM, employees, client counts, custody flags, Item 11 codes), explains the v1A subset and adviserinfo_url, and clarifies roster/publisher posture. An agent has everything needed to call and interpret results.

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 coverage is 100% so baseline is 3, but the description adds real meaning: min_aum 'requires the default aum_total sort', firm_type drives whether Item 5F AUM is populated, and CIK is the join key to 13F/enforcement. It goes beyond the schema on the keys an agent must reason about jointly.

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+resource: 'Returns SEC Form ADV registry records' and quantifies scope (~17K RIAs, ~6.5K ERAs). It distinguishes the two firm types and names the record granularity (one per CRD), so an agent can tell it apart from siblings like get_enforcement_actions.

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?

Explicit when-to-use: 'Use this when the user asks: who advises/manages money, how big is an adviser, largest RIAs by state, advisers with disciplinary history, or to vet a firm before pairing with enforcement / holdings data.' It names the alternative sibling datasets (enforcement, holdings) and the conjunction condition.

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