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

Annotations already declare a safe read-only, idempotent operation, but the description goes far beyond them: it discloses the access tier behavior (first 5 rows in full, rest locked by type, contact values and decision-maker names never returned), that every answer reports what was withheld in `entitlement` and `locked`, and the SUSB counting rule that multi-state firms count once per state.

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 core purpose is front-loaded in the first sentence and the access caveats are grouped afterward, so an agent can extract the essentials quickly. It is dense and the trailing plans/promo URL is borderline noise, keeping it from a 5.

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 no output schema, the description carries the burden of describing the response and does so: firm counts by size band, DFX-held count, current-with-20+-participants count, coverage percentage, plus the entitlement/locked withholding structure. Nothing needed to call or interpret it is missing.

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 the baseline is 3, but the description adds real meaning beyond the schema: it frames `naics` as a 2-to-6-digit code and `state` as either one state or the whole nation, and clarifies the multi-state counting semantics that the schema cannot express.

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 precise verb and resource: a Census SUSB firm count for one NAICS code and one state/nation, paired with the number of DFX-held companies and a coverage percentage. The concrete example ('how many HVAC contractors are there in Ohio and how many do you cover') makes the output unambiguous without opening the schema.

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 example question and the 'count vs. list' framing clearly signal when to reach for this tool, and the access paragraph explains what you get back. It never explicitly contrasts itself with the sibling 'dfx_coverage' or other coverage tools, so the routing guidance stops short of full sibling differentiation.

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