arr_call

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

With no annotations, the description carries the full burden and delivers: it discloses the confirm gate, the exact confirm_phrase format for destructive classes of calls (delete, restart, backup restore, host/security settings, password changes), the no-query-string constraint on path, and the per-service body rules. This is exactly the behavioral context an agent cannot get from the schema.

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?

Front-loads the one-line purpose, then a labeled block per parameter, then the safety workflow. Length is justified by 8 parameters and a non-obvious confirmation protocol; every sentence is functional and none restates the schema.

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 high-complexity, unannotated, multi-service mutation tool the description covers the safety-critical behavior thoroughly, and the existing output schema removes any need to explain return values. Remaining gaps are secondary: no auth/permission notes, no rate-limit or pagination guidance, and max_chars is unaddressed.

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 supply all meaning and it nearly does: service (with valid values), path (format, examples, and the 'no query string' rule), method (enum), params (query options vs. qBittorrent form fields), body (JSON for POST/PUT, unused by qBittorrent), and confirm/confirm_phrase (trigger conditions and exact format). Only max_chars is left unexplained, a minor omission against otherwise complete coverage.

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 and resource ('Call any API path on a service') and immediately enumerates the services and path forms, making the low-level escape-hatch scope unambiguous next to the specialized siblings like arr_search and arr_status. An agent can tell this is the generic call-through tool without opening 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?

Gives clear when-to-use rules for the write path: GET runs at once, any change waits on confirm=true, and the user must be told and give a clear yes first. It also prescribes the read-before-write workflow ('Never guess a body: read an existing item with GET first'). It never routes the agent to a specialized sibling when one exists, which is the one missing piece.

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