qui_dir_scan

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

There are no annotations, so the description carries the transparency burden. It reveals behavioral intent through operation names and HTTP verbs (DELETE, POST, GET, PATCH) and endpoint paths, making it clear which operations read, mutate, delete, create, or requeue. However, it does not describe side effects such as whether deletes are permanent, what a scan cancellation does, or whether these actions require elevated permissions, so the behavioral picture is only partially painted.

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 every line is a one-to-one operation/endpoint mapping that is useful. The first two sentences front-load the invocation pattern, and the list is sorted and consistently formatted. No filler or repetition exists, though the list of 15 endpoints is necessarily dense.

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 this is a multi-operation dispatcher with 15 endpoints, the description provides a good enumeration plus argument structure rule. However, it does not describe per-operation required parameters, the outcome of each operation, or any caveats needed for safe use. The presence of an output schema removes the need to detail return values, but the behavioral gaps in such a complex tool mean the description is only moderately 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 description coverage is 0%, so the description must add meaning. It does exactly that by explaining how to structure `arguments`—path variables in `arguments`, query values in `arguments.params`, and request bodies in `arguments.body`. This is essential and not present in the input schema. It stops short of documenting per-operation argument names, but the endpoint templates show those placeholders.

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 'qui dir scan operations on qui' and then enumerates 15 concrete operations with endpoints, making it clear that this tool dispatches directory-scan operations. It distinguishes itself from siblings like qui_orphan_scan by focusing specifically on directory scan resources. It lacks a single verb+resource framing but the operation list fully clarifies scope.

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 provides clear instructions for how to invoke the tool: pass an `operation` and an `arguments` object, with path variables, query values, and body placed in the appropriate nested locations. It also lists the exact operations, giving an explicit scope and exclusion boundary—this tool covers dir-scan operations and nothing else. There is no explicit guidance on when to prefer a sibling alternative, but the clear domain and operation set are enough.

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