get_leads

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

There are no annotations, so the description carries the behavioral transparency burden. It discloses that the operation reads results, that Excel is auto-generated alongside CSV after collection, and that only contactable records appear. It does not discuss edge cases such as empty results or errors, but it provides meaningful behavioral context beyond a simple read statement.

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 compact and well-structured: it leads with the core purpose, then adds one useful behavioral note, then gives clear parameter semantics. Every sentence contributes information needed to use the tool correctly, with no repetition or 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?

Given no output schema and no annotations, the description covers the key aspects an agent needs: what the tool reads, how to reference a job or file, status filtering, and result column structure. It is slightly incomplete because it does not explicitly describe the returned data shape for the API call itself, but the provided context is sufficient for most calling scenarios.

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 0%, yet the description documents every parameter in its Args section: job_id is the task id from start_collection, csv_path reads previous sessions, status defines the three allowed values, and limit caps the return count. This fully compensates for 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 opens with a specific action ('수집 결과를 읽는다') and identifies the resource as collection results, also clarifying that it returns only a subset rather than all records. However, it does not explicitly distinguish itself from siblings like export_excel or check_collection, so it stops short of full sibling differentiation.

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 gives clear context for when to use job_id versus csv_path, and explains that status and limit control the returned set. It does not state explicit when-not-to-use guidance or name alternative tools, but the parameter-level usage conditions are genuinely helpful for an agent deciding how to call it.

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