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

Beyond the annotations (readOnly, idempotent, closed-world), the description discloses the crucial result behavior: it returns a match count plus a link, free samples come back in full with specific fields, and every other match is locked with only role type, city and posting language. That partial-paywall disclosure is exactly the kind of thing an agent must know before calling, and it is not in the schema or 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?

Front-loaded with purpose, then return shape, then fit. Three dense sentences with almost no filler; the enumerated field list and the trailing 'fits questions' clause are slightly listy but each carries routing value.

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?

With six optional parameters and no output schema, the description carries the return-value burden itself and does: match count, link, full sample records with named fields, and locked-record fields. Combined with the 100%-covered input schema, an agent has everything needed to call and to explain results to a user.

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 100%, so the baseline is 3; the description earns above that by translating user intents into filter choices — visa sponsorship questions pointing at visa_route, Korean-level questions at the korean filter. It still doesn't define edge behavior like how query interacts with market or what empty query plus filters yields, that being left to the 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?

States a specific verb and resource ('Search open jobs for foreigners on Seoulstart') and immediately scopes the corpus: Korea in-country jobs, remote, global, and AI training work. This is clearly distinguishable from siblings like jobs_overview (aggregates) and visa_sponsoring_companies (companies, not postings).

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 closing sentence enumerates concrete question shapes the tool fits (English-speaking jobs in Seoul, D-10/E-7 visa sponsorship, AI training work), which is real routing guidance that maps user intent to the market/visa_route filters. It stops short of naming when to prefer a sibling such as jobs_overview or housing_* alternatives, so no explicit exclusions.

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