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

With no annotations, the description carries the burden and does well: it discloses the request is queued for user approval, that the user signs and publishes a new policy version, and that direct agent mutation is impossible. It omits failure handling, duplicate-request behavior, and whether the queued request is pollable.

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 short sentences, no waste, with the agent-directed affordance and the approval workflow front-loaded. Every sentence adds a distinct fact.

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?

An output schema exists so return values need not be explained, and the human-approval flow is well covered. But for a 3-required-param tool with 0% schema coverage and no annotations, the description leaves parameter content under-specified, which an agent needs to compose a valid call.

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 0% for all three required params, so the description must compensate. It only illustrates the format of 'request' via the example; 'agent_id' and 'reason' receive no explanation of expected content or format, leaving two-thirds of the parameters undocumented.

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+resource ('Ask the user for a policy/budget change') and gives a concrete example ('raise daily budget from 50 to 80'). It explicitly distinguishes itself from the direct-mutation sibling set_policy by declaring 'Agents can NEVER change policy directly.'

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 line 'Agents can NEVER change policy directly' effectively tells the agent this is the only sanctioned path for policy/budget changes, implicitly excluding set_policy. However, no sibling is named outright and no explicit when-not conditions or fallback alternatives are given.

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