Verify and save a company's board

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

The description adds significant behavioral context beyond annotations: it reveals the conditional save ('Nothing is saved unless postings were seen'), explains the reason (wrong slug answers 200 with generic page), and notes the Workday limitation. This complements the annotations (readOnlyHint=false, destructiveHint=false) without contradiction. No annotation contradiction.

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 two sentences, front-loaded with the core action, and every phrase adds value. It succinctly explains the verification logic and usage context without redundancy. This is concise and well-structured.

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 (8 parameters, no output schema), the description covers the essential behavioral aspects: verification, conditional saving, and the Workday-specific use case. It does not explain every parameter, but the schema covers some, and the description provides enough to invoke it correctly for the main use cases. Slightly more detail on optional parameters would make it complete.

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 50%, with descriptions for name, board, save, and query. The description adds overall context but does not explain undefined parameters like ats, tags, tier, or region. It does reinforce board semantics (e.g., Workday triple) but does not fully compensate for the missing parameter descriptions. Hence a mid-range score.

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 a specific action ('Checks that a candidate board actually serves postings, then saves it to companies.json') with a distinct resource (candidate board, companies.json) and purpose. It also distinguishes from siblings by explaining when to use it ('record boards found elsewhere') and emphasizing Workday, which cannot be probed by guessing.

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?

Explicit guidance is provided: 'Use this to record boards found elsewhere — a careers-page URL or a web search' and explicitly calls out Workday as a case requiring this tool. This implies when not to use it (for probing by guessing, likely via resolve_company_board) and gives clear context for choosing this tool.

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