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

Beyond the annotations, the description explicitly discloses what the tool creates (people, jobs, interview plans as stubs, job postings, applications), that it replays idempotently, and what it never does (send outreach, merge people, delete records). This gives the agent a concrete side-effect model without contradicting the annotations.

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?

Two sentences with no filler: the first front-loads the action and its governing condition, the second compactly lists created and excluded behaviors. Every clause earns its place.

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 mutating apply tool with no output schema, the description covers the purpose, side effects, idempotency, and safety exclusions well. It falls slightly short on explicit parameter guidance for request_id and idempotency_key, and it does not name the dry-run predecessor by tool name, but an agent can still correctly invoke it with the required fields.

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 must explain the parameters, but it only meaningfully clarifies preview_hash ('matching the stored dry-run'). It does not explain import_id, request_id, or idempotency_key, even though idempotent replay is mentioned and idempotency_key is likely relevant to that behavior. The description leaves most parameter semantics to inference.

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 states a specific verb ('Apply') and resource ('ATS import preview'), includes the key condition (preview_hash matching the stored dry-run), and enumerates the entity types created. This clearly distinguishes it from sibling tools like yardstick_ats_imports_dry_run, yardstick_ats_imports_read, and yardstick_prospect_imports_apply.

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 makes the usage context clear: apply only an approved ATS import preview whose preview_hash matches the stored dry-run. It implicitly routes the agent toward the dry-run-then-apply workflow and away from read-only or preview-only tools, though it does not explicitly name alternatives or give when-not conditions.

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