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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and closed-world, so the safety profile is given. The description still adds real value beyond them: the required credential scope, the 403 on unclaimed sandbox workspaces, and how an agent key narrows the visible set to its own policy plus the workspace default. It does not describe pagination or response shape, so it is solid but not exceptional.

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?

Three sentences, each carrying distinct load-bearing information: what is returned, what credential scope is required, and which workspace state is a hard prerequisite. Purpose is front-loaded and the long parenthetical enumerates return fields rather than padding.

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?

There is no output schema, yet the description compensates by enumerating the returned policy facets, the defaults, and today's reservations. Combined with the credential and workspace-claim prerequisites, an agent has everything needed to predict success or failure before calling.

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 100% and there is only one optional parameter, whose schema text already says it names the policy governing a given agent. The description's note that "an agent key sees its own policy and the workspace default" hints at scoping behavior but refers to the auth key rather than to agent_id, so it adds only marginal meaning over the schema.

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?

Opens with a specific verb+resource ("Read the spend policies") and enumerates the exact contents returned: per-purchase max, daily UTC cap, approval gating, seller/category scope, save-time defaults, and today's reservations. It is unmistakably a read of spend policy rather than the write-side set_spend_policy, but it never explicitly names a sibling (e.g. list_commerce_policies or get_commerce_policy) to sharpen the boundary.

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 clear conditions for successful use: needs a Last Price credential with routing read scope and a claimed workspace; a self-registered sandbox key gets a 403. It also explains the agent-key viewing scope. It stops short of naming an alternative tool to call instead in any scenario, so it is context rather than explicit routing.

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