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

Annotations already cover the safety profile (readOnly, openWorld, non-destructive), yet the description adds real behavioral detail beyond them: GSA truncating values after a colon, statistics being withheld rather than reported misleadingly, and unchanged source statistics for empty/thin samples. The disclosure is valuable but the sentence describing the verification gate ('non-approximate requested-field aggregation proves every rate row...') is jargon-dense enough that an agent may not fully parse what triggers withholding.

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, prerequisite, and field list are front-loaded and efficient, but the final paragraph is a single dense block that mixes API quirks, tool internals, and disclaimers without breaks. Every sentence has a reason to exist, yet the phrasing could be far tighter.

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?

The output schema excuses it from explaining return values, but for a 12-parameter tool with zero schema descriptions the omission of filter and pagination semantics is a real gap — an agent cannot know how price_min/price_max or business_size interact with the exact-match requirement. The description fully covers matching semantics but under-covers the tool's actual parameter surface.

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 0% across 12 parameters, so the description carries the full burden — but it only explains the `field` enum values (adding useful meaning to idv_piid as the GSA MAS contract number) and leaves page, sort, ordering, page_size, price_min/max, business_size, and the experience/education filters entirely undiscussed. Nine filter/pagination parameters are undocumented in both places.

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 and resource ('Exact match search on a specific field') and immediately enumerates the searchable fields (labor_category, vendor_name, idv_piid), which also disambiguates it from keyword_search's substring behavior. An agent can tell exactly which tool performs which style of matching 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?

Gives an explicit prerequisite — 'Use suggest_contains() first to discover the exact field value' — and a hard failure condition: partial matches return 0 results. It also names the fallback path (keyword_search recovery guidance) for the colon-value case, so when-to-use, when-not, and alternatives are all covered.

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