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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds materially useful context beyond them: the per-call price of $0.005 USDC via x402, which is a real cost/authorization constraint an agent must know before invoking. It omits any rate-limit, pagination, or result-size behavior.

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?

Three tight sentences with the resource and modes front-loaded; the pricing sentence and the audience sentence are both short and earn their space. Slightly dense phrasing around the two operating modes, but no filler.

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 4-parameter, no-output-schema tool at 25% schema coverage, the description leaves gaps: `limit` has no stated meaning or maximum, pagination behavior is unstated, and the mismatch between the `location` input and "locations" in the output is unresolved. Cost and source coverage are covered, which keeps it at minimum-viable rather than inadequate.

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 only 25% (just `q` is documented as "Title keywords"), so the description carries real burden. It partly compensates by implying `company` selects a full board and `q` drives remote keyword matching, and by confirming that location appears in results, but `limit` and the distinction between the `location` parameter and the returned locations are never explained.

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 concrete resource and two distinct modes: full company boards (Greenhouse, Lever, Ashby) versus keyword-matched job postings, plus the returned fields. It does not differentiate itself from the sibling `jobs` tool, which appears to overlap heavily, so the sibling-boundary work is left undone.

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?

"Useful for sales signals and recruiting" gives a domain context for when the data matters but offers no when-to-use/when-not-to-use guidance and never names the alternative (`jobs`) that an agent would have to choose between. Usage is implied rather than directed.

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