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

Annotations only declare readOnlyHint=true, so the description earns credit for adding the result shape (id, title, snippet, relevance, resource type), the fields='*' expansion behavior, and the hard 30-result cap. Pagination/offset behavior and what happens when results exceed 30 are not addressed, keeping it short of a 5.

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?

Two sentences plus the backing endpoint, front-loaded with the scope statement, then return shape and limits. No filler and every clause carries information.

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 correctly compensates by naming the returned fields and the expansion option, and it documents the result cap. It is nearly complete for a search tool, missing only query-language guidance and what to do when the cap truncates results.

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. The description echoes the fields='*' trick and the 30-result ceiling that the schema already states, and its mapping of 'conversations (cases), users and organizations' lightly helps decode the USERS/ORGANIZATIONS/CONVERSATIONS enum for the resources parameter, but adds little genuinely 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?

States a specific verb and resource set: 'Unified search across conversations (cases), users and organizations.' The word 'unified' plus the resource list distinguishes it from siblings like kayako_list_cases, kayako_list_users and kayako_search_help_center. However it never explicitly contrasts itself with those list tools, leaving the differentiation implicit rather than stated.

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 'unified search' — reach for this when you need free-text matching rather than enumeration. But there is no explicit when/when-not, and no mention of the sibling kayako_search_help_center, which covers the article domain and is the obvious alternative an agent might confuse this with.

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