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

Annotations indicate the tool is not read-only (readOnlyHint: false) and not idempotent, which aligns with a mutation operation. The description adds context about the mutation ('Change the role' and 'Send role: null to clear it'), but does not disclose side effects (e.g., whether it overwrites existing roles, requires specific permissions, or affects other people on the node). With annotations already marking it as non-read and non-idempotent, the description provides moderate added value but not full transparency.

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 a single sentence with a follow-up clarifying the null case. It is concise and front-loaded with the essential action. The example and clear-instructions earn its place without excess. However, it could be slightly more structured (e.g., splitting guidelines from the primary purpose).

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?

Given 5 parameters, 40% schema coverage, no output schema, and the tool being a mutation, the description is somewhat complete but falls short. It explains the role parameter's null behavior but omits context for orgId, nodeId, teamId, and personId beyond what the schema provides. The tool's behavior (e.g., what happens if personId doesn't exist, or if nodeId is invalid) is not addressed. For a mutation with moderate parameter count, more contextualization is needed.

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 40%, meaning 2 of 5 parameters (nodeId and personId) have descriptions in the schema. The tool description adds meaning beyond the schema for the 'role' parameter by explaining its semantics ('Send role: null to clear it'), which is not present in the schema. However, parameters like teamId and orgId lack any additional explanation in the description, so there is still a gap. The null-handling tip is valuable for correct usage.

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 starts with a clear verb ('Change') and identifies the resource ('the role a person plays in the process behind a process landscape node'). It also provides a concrete example ('Approver') and explains how to clear the role ('Send role: null'). This distinguishes it from addClarityLandscapeNodePerson (add) and removeClarityLandscapeNodePerson (remove) in the sibling list, though it does not explicitly differentiate from them.

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 implies usage for updating or clearing a role on an existing person-node association, but it does not specify when to use this tool versus addClarityLandscapeNodePerson (for assigning a new person) or removeClarityLandscapeNodePerson (for removing a person entirely). There is no guidance on prerequisites (e.g., the person must already exist for this node) or exclusions. The null-clearing hint is helpful but incomplete for full decision-making.

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