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

Annotations already declare read-only, open-world, idempotent, non-destructive, so the safety profile is covered; the description then adds substantial extra context: no emails/phones/home addresses are returned, ambiguous or unmatched inputs return a free row with row_status, failed runs return an error with a run ID, an APIFY_TOKEN is required, and Apify credits are consumed per matched row (with max_charge_usd truncating the run).

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?

It is a single dense but well front-loaded paragraph where essentially every clause carries information (modes, coverage, privacy, errors, auth, cost). It could be easier to scan with the mode/coverage/privacy facts broken out, but there is no 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?

For a 15-parameter, three-mode, no-output-schema tool, the description supplies the return contents, geographic limitations, per-call cost/auth requirements, and error/ambiguity behavior, which is everything an agent needs to invoke it correctly without an output schema.

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 baseline is 3 and the schema already documents all 15 parameters including mode, per-line formats, and defaults. The description adds the size-band breakdown (1, 2-15, 16-50, 51+) and per-mode state coverage, but little parameter syntax beyond the schema.

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 opening sentence states a precise verb and resource ('Look up a licensed US real estate agent on the official state license register') and enumerates the concrete outputs (brokerage of record, active agent count, size band, license status and expiry). An agent immediately knows what this tool returns and the scope of the data.

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?

It explicitly names the three operating modes and the condition selecting each: lookup (one agent or a list, by license number or name), roster_firm (active agents at one brokerage), and roster_zip (offices in a zip, NY/MO/OR/VT). It also states coverage boundaries ('Covers 19 states; brokerage data in CA, IA, MO, NV, NY, OH, OR, TX, VT'), which steers the agent away from unsupported queries.

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