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

Annotations already declare readOnlyHint=true, and the description is consistent with that. It adds useful context (these runs are blocked on approval and invisible to the client), but says nothing about pagination, ordering, or result size for a list operation, so it adds some value rather than a lot.

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, both earning their place: the first defines the resource and its scope, the second gives the follow-up action. Scope is front-loaded and there is no filler.

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 zero-parameter, read-only listing with no output schema, the description covers what the agent needs: who the items belong to, why they are pending, and which tools resolve them. Minor gap is the absence of any note on volume or ordering.

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 tool takes zero parameters, so the description has nothing to compensate for beyond noting the implicit scoping to the coach's own clients — which it does. Baseline 4 applies for a parameterless tool.

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 (list) and resource (AI runs) plus a precise scope: the coach's own clients, pending approval, not yet shown to the client. It reads distinctly from candidates like list_workflow_approvals, though it never names a sibling to explicitly differentiate itself.

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?

Gives a clear workflow: show the rationale and artifacts to the coach, then call approve_ai_run or reject_ai_run. This tells the agent what to do after the list, but it does not say when not to use this tool or how it differs from get_client_ai_history or list_workflow_approvals.

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