qui_instances

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

No annotations are provided, so the description must carry the full burden. It reveals the tool is a router/aggregator for multiple sub-operations, which is critical behavioral info. However, it does not disclose mutation risks (e.g., qui_delete_instance permanently deletes, qui_update_instance modifies settings) or whether operations are safe/idempotent. This is a significant gap for a tool with 17 operations, many of which are mutating.

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 list is compact and front-loaded with the general pattern, then each operation with its endpoint. It's efficient for a router with 17 operations. The opening two sentences explain the calling convention. The list is a necessary enumeration for completeness, though it makes the description long; still, every item adds value.

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 (17 operations) and absence of annotations, the description gives the operation list and basic argument structure, but lacks per-operation parameter details, expected responses, or error handling. It has an output schema, which partially compensates. For an agent to correctly call this tool, it needs more per-operational detail (e.g., required fields for qui_create_instance), so it's only minimally complete.

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 has 2 params: operation (enum) and arguments (loose object with anyOf null). The description adds crucial semantics for arguments: path variables go directly, query values in arguments.params, JSON body in arguments.body. This is genuinely helpful. However, it does not explain per-operation argument requirements (which operations need instanceID, what fields for creation/update), leaving the agent to infer from endpoint paths. Schema coverage is 0%, so more compensation was needed.

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 enumerates 17 operations with their HTTP endpoints, clearly indicating this is a dispatch router for instance-related actions. It specifies the resource (instances) and the action spectrum, distinguishing it from sibling tools that target other domains (torrents, RSS, backups). However, it lacks a general one-line summary, relying on the list to convey purpose.

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 implies usage: pass the operation and an arguments object with path variables, query params, and body. It does not explicitly state when to use this tool versus alternatives (e.g., qui_torrents for torrent-specific actions). The context implies all instance operations go here, but exclusions or comparator guidance are absent.

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