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

Annotations only declare readOnlyHint=true, yet the description adds the required permission scope ('Needs billing.read'), confirms 'Read-only', and explains the functional consequences of crossing the thresholds — unattended runs degrade to the quick tier past the soft cap and are refused past the hard cap for the rest of the UTC day. That is substantive operational context an agent cannot get from the annotations.

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?

One dense paragraph, front-loaded with the resource identity and followed by field-by-field disclosure and the cap consequences. Every sentence carries information, though the stacked parentheticals and the CLI-twin reference make it heavier to parse than necessary.

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, so the description must describe the return payload, and it does — enumerating the cap fields, the effective cap, today's spend, and token caps. Combined with the permission note and the degradation semantics, nothing an agent needs in order to call this correctly 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?

The tool takes zero parameters, so the baseline is 4 and the schema carries all it needs to. The description spends its detail budget instead on the null semantics of daily_chat_usd_cap ('null when the plan default applies'), which is return-value meaning rather than parameter meaning.

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 and resource ('The organisation's AI spend cap') and immediately enumerates the exact fields returned, including daily_chat_usd_cap, the plan default, the cap in force, and today's tokens. It also names the mutating sibling set_ai_spend_cap, so an agent can separate this read from the write without opening either 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?

The clause 'set_ai_spend_cap changes them' gives an explicit read-vs-write routing rule. It also supplies the prerequisite 'Needs billing.read', which tells the agent when the call will fail. It stops short of stating explicit 'do not use when' conditions or naming other spend-reading siblings, so it is strong but not exhaustive.

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