Show plan and quota, or upgrade

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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds materially richer behavioral context: start_trial is a real account change, open launches a checkout page in the user's browser, neither charges a card by itself, an API key is required, and the returned quota snapshot already reflects a same-call trial. No contradiction with annotations exists.

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?

The description is front-loaded with the purpose, then explains usage, then covers safety and authentication. It is slightly longer than strictly necessary, with minor overlap between 'No billing state changes unless you pass start_trial' and 'Neither charges a card by itself,' but the length is justified given the tool's dual read/action nature.

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?

Given the tool's complexity, three optional parameters, and no output schema, the description is remarkably complete. It covers default read behavior, what the read mode returns, when to use it, the side effects of both action arguments, API key requirements, trial behavior, and how it relates to the `status` sibling. An agent can safely decide when and how to invoke this tool.

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?

Since the input schema has 100% description coverage, the baseline is 3. The description adds value by clarifying that passing either argument shifts the tool from reporting to acting, that these arguments should only be passed on explicit user instruction, and that plan defaults to the recommended plan. It reinforces safety-critical semantics without merely repeating 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?

The description opens with a specific purpose: 'Show the account's current plan, how much of each quota remains, and what a higher plan unlocks.' It clearly differentiates the no-argument read mode from the two-argument action mode, and the title reinforces this dual behavior. This distinguishes it from siblings like status, which is about authentication rather than plan/quota information.

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 description gives explicit usage guidance: called with no arguments it only reads and is 'useful any time, not just after hitting a limit,' and it is 'the natural follow-up when a write tool reports a quota error.' It explicitly warns that arguments should be passed 'only on explicit instruction from the user' and directs authentication questions to the sibling tool `status`, providing both when-to-use and when-not-to-use guidance.

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