get_users_subscriptions

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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: auth is injected server-side and never handled by the model, calls are throttled under a 30-per-10s cap and retried on 429/5xx, and the full error surface is mapped (401/403/404/422). 'Creates, changes and deletes nothing' is consistent with readOnlyHint=true — no contradiction.

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 long but earns its length through labeled sections (Behavior, Parameters, Returns, Use when) and front-loaded identification (READ-ONLY, GET endpoint, action). Each sentence carries functional content; the emoji markers aid quick scanning. Slightly heavier than strictly necessary, but nothing is filler.

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 simple 3-parameter, 0-required, no-output-schema lookup tool, this is complete: pagination mechanics, parameter combination, return envelope, error-to-tool-error mapping, API-rate expectations, and speculative use guidance are all covered. An agent can select and invoke this tool correctly with no further investigation.

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%, so the schema already documents all three parameters, setting the baseline at 3. The description adds value beyond the schema by explaining combination semantics ('if more than one Query param is provided, then all of them will be applied — AND operator') and by explicitly instructing the agent to walk pages with the page parameter. This exceeds the baseline.

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 names a specific verb and resource ('Get users subscriptions. Returns a list with the user subscriptions') and adds distinguishing detail: descending sort by user creation date, 20-per-page pagination, and AND-combination of query params. This clearly separates it from the many other get_* lookup siblings without needing to inspect the 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?

Explicit when-to-use ('safe to call speculatively for lookups and reporting') and when-not-to-use ('Not for changing anything') are both present. The alternative is referenced only by category ('the matching 🟡 write tool') rather than by a named sibling tool ID, and no matching write-subscription sibling appears in the tool list, so the pointer is slightly unactionable.

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