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

Annotations already declare the read-only, idempotent, non-destructive, closed-world profile, so the description's burden is lower. It still adds meaningful context beyond them: results carry 'review status and source,' signalling that figures are curated and may vary in verification level — useful for judging trustworthiness. It does not disclose coverage gaps or staleness windows.

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?

Two sentences: the first front-loads what the tool returns and the product coverage, the second delivers the invocation hint. No filler, no restatement of the title, and the parenthetical field list is compact.

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?

For a read-only, no-output-schema lookup with two optional filters and rich annotations, the description supplies enough: payload fields (messages, credits, rate limits, reset windows), provenance metadata, and the no-arg behavior. Minor gap: it doesn't state whether plan alone is a valid query or how the two filters combine.

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 both parameters are optional, so the baseline is 3. The description earns above baseline by explaining the zero-argument case ('Call with no product to list covered products') — meaning not present in the schema, which otherwise reads as a plain filter. It stops short of clarifying product+plan interaction or plan-only queries.

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 gives a specific verb+resource ('Documented usage limits ... for AI products and plans') and enumerates concrete products (ChatGPT, Claude, Gemini, Copilot, Cursor, etc.), so the agent knows exactly what domain of data is returned. It does not explicitly distinguish itself from siblings like compare_subscription_plans or get_model_prices, leaving the boundary between 'limits' and 'plans/prices' to inference.

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?

One concrete invocation pattern is given: 'Call with no product to list covered products.' This implies the optional-parameter behavior usefully. However, there is no guidance on when to reach for this tool versus compare_subscription_plans or get_model_prices, and no statement about whether 'plan' can be used alone as a filter.

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