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

No annotations exist, so the description carries the full burden, and it does disclose the meaningful non-obvious behavior: this is a multi-step composition that first derives a category slug and then fetches listings, which implies extra latency and automatic category inference. It also states a hard input constraint ('Never pass slug=all'). It stops short of return shape, failure modes, or pagination behavior.

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?

Three short sentences, zero filler, with the identification and the preference stated first. The compressed arrow phrasing in the first sentence borders on cryptic, which costs a point on clarity but not on economy.

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?

The description covers routing and the input contract, which is the core need, and there is no output schema so return values needn't be explained. However, for a composite pipeline tool it leaves the agent without any sense of what comes back or how paging continues via search_next_page, which is a real gap for a search entry point.

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 every parameter is already documented, and the description mostly echoes that by restating the term/query duplication rule. The one addition, 'Never pass slug=all', references a parameter name that does not appear in the schema (only step_38_url_query_region_slug exists), which adds a rule but also mild ambiguity. Baseline 3 is appropriate.

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?

Names a specific verb and resource (Jiji keyword search) and gestures at the internal pipeline (suggest → auto category slug → listings), which tells the agent this is a composite, not a raw listing query. It distinguishes itself from the sibling search_listings via 'Preferred for product search'. The arrow notation is terse and forces some inference about what the tool actually returns, keeping it below a 5.

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?

'Preferred for product search' gives an explicit default-selection rule against siblings like search_listings, search_suggest, and browse_listings, and 'Never pass slug=all' supplies a hard exclusion. It does not, however, say when to prefer search_suggest alone or when to move to search_next_page, so the routing picture is only partially complete.

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