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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real context beyond that: the default PENDING scoping, the admin-only approverId behavior, the WorkflowApproval return type, and a PRO+ plan gate requirement.

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?

Four tight fragments, each earning its place: identity, default behavior, alternate scope, preferred alternative, plan gate. Front-loaded with the resource and 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?

No output schema exists, and the description names the returned row type, which is the key return context. Pagination is only implied via the limit param in the schema; a note on ordering or result size would complete it, but nothing essential for correct invocation is missing.

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 coverage is only 33%: limit is documented inline but status and approverId are bare in the schema. The description compensates by explaining status's PENDING default and the admin-scoped meaning of approverId, adding genuine meaning beyond the structured fields.

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 resource (the caller's workflow-approval inbox / WorkflowApproval rows) and immediately distinguishes it from the action sibling decide_workflow_approval. An agent can tell this is the read/list side of workflow approvals without opening the schema.

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?

Explicitly says the default is status=PENDING and what that means (your queue), gives the alternative path for inspecting another user's queue via approverId (admins only), and names the tool to prefer for acting on a row. When-to-use and when-to-use-something-else are both covered.

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