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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral context beyond the annotations: results include license number/status from public records, price ranges, service radius, booking URLs, and the distinction between claimed_by_owner providers and providers seeded from public records. This helps the agent understand data provenance and result semantics.

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 description is lengthy but dense, with each clause adding useful information such as result fields, filtering behavior, a usage example, and data provenance. It could be slightly tightened, but the length is justified given the absence of an output schema and the need to explain marketplace-specific data attributes.

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 read-only search tool with no output schema, the description covers the core semantics: what is being searched, what fields appear in results, how filtering works, and where the data comes from. Pagination is left to the schema, and response structure is not described, but the description provides sufficient context for correct invocation.

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 75%, and the description compensates by clarifying that category can be a name or slug, is matched loosely, and provides concrete category examples. The example payload ('{"category": "general contractor", "city": "Pasadena"}') adds practical parameter guidance. Cursor and limit are not elaborated in the description, but they are documented in 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 description opens with a specific verb and resource: 'Find contractors, designers, permit expediters and trades for ADU work on the A-du services marketplace.' It enumerates the service categories and clearly identifies this as the marketplace search tool, distinguishing it from sibling tools like search_plans, search_rentals, and search_managers through the explicit services-focused scope.

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 description gives a direct use-case example ('Use for "find me a contractor to build an ADU in Pasadena"') and explains filtering by category and city. It does not explicitly state when not to use this tool versus alternatives, but the example and resource scope make the intended usage clear.

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