list_adapters

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

The description adds extensive behavioral context beyond the readOnlyHint/idempotentHint annotations: the stale threshold logic (3 intervals + 15 minutes), the clock references (appliance vs local), pagination semantics (next_offset null termination), and the gotcha that recent last_collected does not prove all objects receive data. It also discloses that empty/unrecognised answers are errors, not empty lists. No contradiction with 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?

Though lengthy, the description is well-organized into When/What/Gotchas sections and front-loaded with the core purpose. Every sentence earns its place — the field listing compensates for the missing output schema, and the stale and clock explanations are essential. No fluff or redundancy.

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?

With no output schema, the description carries the full burden of explaining return values, and it does so thoroughly: row fields, stale/stale_basis logic, clock references, the paginated envelope with next_offset termination, and error behavior. For a read tool with 4 documented parameters and rich annotations, nothing an agent needs to call it 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?

Schema coverage is 100% and each parameter already has a solid description (limit range, offset pass-through, target config, adapter_kind case-insensitivity). The description reinforces limit/offset usage through the pagination envelope explanation and introduces adapter_kinds_present which helps interpret the adapter_kind parameter. It adds context but doesn't dramatically extend schema semantics.

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 verb+resource pair: 'List Aria Operations adapter instances and when each last collected.' It distinguishes itself from sibling tools like list_collector_groups (collector processes) and get_aria_node_resources (node memory), making its scope unmistakable.

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?

It explicitly names when to use: 'When: an alert such as "Objects are not receiving data", or metrics that stopped updating', and names alternatives: 'For the collector processes behind them use list_collector_groups; for the Aria node's own memory use get_aria_node_resources.' No inference required.

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