Search test cases

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

The readOnlyHint annotation covers the safety profile, and the description adds two genuinely non-obvious behavioral facts beyond it: the KIWI_PROJECT default scoping when plan/product are omitted, and the truncated result list with a total count. These affect how an agent interprets results, which the annotation alone does not convey.

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 totaling about 26 words: the first front-loads the core purpose, the second explains default context, the third covers return shape. Every sentence earns its place with zero filler or redundancy.

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 no output schema, the description properly covers return values ('total and a truncated list') and the default project behavior that could otherwise surprise an agent. It is adequately complete for an 11-parameter read-only filter tool, though it does not explicitly explain how to page beyond the truncation limit.

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 100%, so the baseline is 3; each parameter's meaning is already fully documented. The description adds a modest cross-parameter semantic (KIWI_PROJECT fallback when plan/product are omitted) but otherwise just compresses the schema's parameter list without new meaning.

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 uses a specific verb+resource construction ('TestCase.filter') and names eight concrete search dimensions (text, plan, status, priority, category, tag, component, automation), making its role as a multi-criteria search tool unmistakable. This clearly distinguishes it from siblings like kiwi_get_case (single-case retrieval) and kiwi_update_case (mutation).

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?

Usage is implied by the filter dimension list and the KIWI_PROJECT fallback note, letting an agent infer this is the general case-search tool. However, there is no explicit when-to-use versus alternatives guidance, no exclusion statement (e.g., 'use kiwi_get_case for a known ID'), and no named sibling comparison.

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