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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so safety is covered. The word 'bounded' adds a useful hint that results are capped, but the description never explains pagination (cursor/next link), ordering, or rate limits — behaviors an agent needs when the result set is large.

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, front-loaded with the core action and followed by the return contents and the practical question it answers. No filler; slightly dense field lists but still readable.

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?

Mentions what the results contain, which partly compensates for the missing output schema, and annotations cover the safety profile. However, for a paginated list tool with 6 parameters, the absence of any pagination or result-ordering explanation leaves a real gap.

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 83%, so the schema already carries parameter meaning; the description adds nothing about limit, state, cursor, or time bounds. The listed statuses loosely map to the state enum but omit 'future' and 'failed' and introduce 'trialing', which is not an enum value.

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 ('Return bounded Recurly subscriptions') and enumerates the data included (account, plan, state, pricing, trial, renewal, cancellation, expiration). It is distinguishable from recurly_list_accounts/invoices/transactions, though it does not differentiate itself from the generic sibling 'list_subscriptions'.

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 second sentence implies a use case ('Answers which customers are active, trialing, paused, canceled, or expiring'), which hints at filtering by state. But there is no explicit when-to-use / when-not guidance, no mention of when to prefer list_subscriptions, and no advice on combining state filters with time bounds.

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