apply_answer_screening

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

With no annotations, the description fully discloses behavior: deterministic, no network calls, honesty rules for specific question types, and the source field for answers. This gives the agent a complete understanding of the tool's operation.

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 structured with a main statement and bullet points for rules, making it easy to parse. While not extremely concise, every sentence adds value. Slightly more conciseness could be achieved, but it is well-organized.

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 that an output schema exists, the description adequately covers the tool's behavior: when to return an answer, when to flag needs_human, the honesty rules, and deterministic nature. No gaps are present.

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?

The input schema covers both parameters with descriptions. The description adds context that the question can be in EN or FR and that the CV path is absolute, which goes beyond the schema. With 100% schema coverage, baseline is 3, and the additional context merits a 4.

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 that the tool answers screening questions factually from the CV or flags needs_human. It specifies verb 'answer' and resource 'screening question', and the honesty rules distinguish it from other apply_* tools.

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 rules for when to return needs_human (e.g., work authorization, salary) and when to return a factual answer. It does not explicitly state when not to use the tool, but the context is clear and the rules serve as usage guidance.

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