search_jobs

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

With no annotations supplied, the description carries the full burden. It does disclose valuable behavior: partial-failure semantics via errors (companies whose collection failed) and manual_check (pages that cannot be scraped and must be read by hand), plus the rule that postings with unknown career are retained. It says nothing about network cost, rate limits, latency, or how many companies are typically hit.

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?

A front-loaded purpose sentence followed by one bullet per parameter and a single return-value line. The inline examples add disambiguation value rather than filler, and nothing is repeated from the schema.

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?

There is no output schema, and the description correctly covers the three return keys (jobs, errors, manual_check), which is the key completeness requirement. Minor gaps remain: it never says where 'the list' of companies originates or whether the call performs live network collection each time.

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 description coverage is 0%, so the description must compensate entirely, and it does: keywords match title or job tags case-insensitively with concrete examples, max_career is defined as a ceiling on minimum required career with the None-career retention rule, categories restrict by company classification, and exclude_keywords match the title. Each parameter gains meaning the bare schema cannot convey.

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 opening sentence states a specific verb and resource ('collect job postings from all companies in the list') and adds scope ('first-pass filter'), so the agent knows this is a broad aggregation-plus-filter step. It does not explicitly contrast itself with siblings like fetch_jobs or get_job_detail, leaving the boundary to inference.

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 phrase '1차로 거른다' (first-pass filter) implies this is the initial narrowing step before detail lookups, which is useful context. However, there is no explicit statement of when to prefer this over fetch_jobs or get_job_detail, and no mention that the company list must first come from list_companies.

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