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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so safety is covered. The description adds structural behavior beyond that — which views require naics, which take no filters, and what each view returns conceptually — though it does not cover pagination, rate limits, or result caps.

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 purpose is front-loaded and the bullet list maps cleanly onto the view enum, so every line is load-bearing. The find_codes bullet is dense and long, but the structure keeps it navigable rather than wasteful.

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?

Given six views, a free-form filters object, and an existing output schema, the description supplies enough to select a view and shape inputs correctly. It stops short of describing cross-view constraints or result limits, but nothing essential for a correct call 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?

With schema description coverage at 0%, the description carries the burden and mostly succeeds: it defines naics as 6-digit, explains each view value, defines board options (biggest, least_crowded, most_open) and that naics is unneeded, and enumerates find_codes filters with enum values for set_aside_family and sort_by. It leaves filter applicability to non-find_codes views and filter value formats unspecified.

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 line names a specific verb and resource — sizing a NAICS market, its winners, and buying behavior across agencies — and enumerates six concrete views (size, competition, solicitation_language, small_buys, leaderboard, find_codes) that map to the enum. This lets an agent distinguish it from sibling search(contracts) without opening a 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?

It explicitly states which inputs apply where: a 6-digit naics for per-code views that take no filters, and routes the agency-scoped case to search(contracts) with naics and agency. It also notes leaderboard needs no naics and warns that find_codes keywords match NAICS titles, not topics ("use 'computer', not 'cybersecurity'"), which is a concrete when-not.

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