systemUsers

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

The annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds extra value by scoping the users to transport-tool semantics and by warning about the scale of the full list ('several hundred entries', 'whole address book')(The schema description also mentions this, but the wording in the tool description helps form the expectation of a read-only query that may produce a large result if unfiltered). This is useful behavioral context beyond the 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?

The description is two sentences and relatively concise. It opens with what the resource is, then gives the travel recommendation about the filter. The first sentence is a bit dense and not a verb-first action, but it avoids fluff and quickly gives the key context. It earns a 4 for being efficient and organized.

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?

For a simple read-only list/search with two optional parameters and no output schema, the description covers the purpose, the parameter semantics (through the schema), and the scale caveat. It doesn't explicitly state the shape of a returned user object, but that is often not expected for a list tool and the tool name suggests users. Given the annotations and required params, this is sufficiently complete.

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?

The schema covers 100% of the parameters and gives detailed descriptions for limit (default 50, counts everything found) and filter (case-insensitive substring on id/name, whole list if absent). The description does not add any meaning beyond the schema; it only reiterates the advice to search with a filter. With full descriptive schema, 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?

The description identifies the resource (system users) and the context ('as the transport tools offer them', 'who a request can be handed to or shared with'.) It does not use an explicit verb like 'list' or 'search', instead describing the content, but the meaning is clear and it is distinct from transport-related sibling tools by emphasizing that these are users eligible for request handoff. It is not tautological and conveys a specific business scope, though it could be more direct about the operation being a listing/search.

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 description explicitly directs the agent to use the filter: 'Search with filter rather than reading the whole address book of the system.' This gives clear context: when you need to find a user among potentially hundreds, you should apply a filter instead of pulling the full list. It does not name alternative tools or state when to use this tool instead of a different one, but the behavioral guidance within the tool is strong, so it earns a 4.

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