keycloak_list_groups

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

The readOnlyHint annotation already covers the safety profile, so the description's burden is reduced. It adds real behavioral value beyond the annotation by disclosing that groups form a tree and that the response nests subGroups inside top-level groups — important for an agent expecting a flat array. It does not contradict the annotation and provides the key response-shape insight an agent needs.

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 totaling roughly 25 words with zero filler. The purpose is front-loaded, and the tree/nesting disclosure earns its place because it shapes the agent's expectation of the response structure. Nothing extraneous could be removed without losing 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?

For a tool with 7 optional parameters and no output schema, the description covers the most critical return-value behavior (tree nesting) while the rich schema documents parameter semantics. The readOnlyHint annotation completes the safety picture. A minor gap is that pagination's interaction with the nested tree structure is never clarified, but this is a subtle edge rather than a blocking omission.

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 86% (6 of 7 parameters documented), which exceeds the 80% threshold, so the baseline of 3 applies. The description itself adds little parameter-level meaning; its tree-nesting note is about output shape, only marginally relevant to briefRepresentation. The schema's parameter descriptions (e.g., q's attribute-search syntax, max bounds, pagination offset) carry the heavy lifting, so no penalty but also no bonus.

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 ('List') and resource ('the realm's groups'), making the core purpose unambiguous. It adds a genuinely distinguishing structural detail — top-level groups come back with subGroups nested inside — which clarifies what the agent will receive. However, it does not explicitly contrast with siblings like get_group, get_user_groups, or get_group_members, so it stops short of full sibling differentiation.

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 purpose statement 'List the realm's groups' implies the usage context: call this when you need the full realm group hierarchy rather than a user's groups or a group's members. But there is no explicit when-not guidance or naming of alternatives, despite 46 siblings including several overlapping group tools. The guidance is implied, not stated.

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