Greenhouse MCP

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: pagination mechanics ('Fetches candidates in pages'), filtering approach ('filters client-side'), and result limitations ('Returns up to max_pages * per_page candidates scanned'). It doesn't mention error conditions or rate limits, but covers the essential operational behavior well.

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 efficiently structured: purpose statement first, usage guidance second, implementation details third, and example last. Every sentence adds value with zero waste. The example is concise yet illustrative of the substring matching behavior.

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 the tool's complexity (client-side filtering workaround) and the presence of an output schema (which handles return values), the description is quite complete. It explains the workaround nature, pagination approach, and result limitations. It could mention performance implications of scanning many pages, but covers the essential context well for a search tool.

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 0% schema description coverage, the description compensates well. It explains the 'name' parameter's purpose and provides an example. While it doesn't explicitly detail 'per_page' and 'max_pages', their roles are implied in the pagination context ('max_pages * per_page candidates scanned'). The description adds significant value beyond the bare 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 clearly states the specific action ('Search candidates by first or last name') and resource ('candidates'), with details about the matching behavior ('case-insensitive substring match'). It distinguishes from siblings like 'list_candidates' by specifying name-based search functionality.

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 provides explicit usage guidance with concrete examples ('when a recruiter says "pull up John's application" or "find Sarah Chen"'). It also explains the technical context ('filters client-side since the Greenhouse API doesn't support name search directly'), giving clear when-to-use reasoning.

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