use_tool

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

The annotations only declare readOnlyHint=false, so the description carries most of the burden and does add the key fact that this is a proxy executing an arbitrary named tool. However, nothing is said about the risk profile depending entirely on the target tool, what happens if the tool name is unknown or the arguments do not match the target's schema, or what the call returns. For a dynamic dispatcher these are significant undisclosed behaviors.

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?

Two short sentences, front-loaded with the action before the conditional usage rule, with no filler. The phrase 'this app does not show the new tools yet' is slightly vague about what 'not shown' means, but it is not padding.

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, three parameters including a free-form nested object, and non-read-only semantics, the description should say more about return behavior and failure modes. It adequately explains why to call it and what to pass at a high level, but leaves an agent guessing about results and error handling for a complex dispatch tool.

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 67% and the schema already documents 'tool' with an example and 'dry_run' meaning. The description only repeats the tool+arguments pairing without explaining the critical semantic that 'arguments' must conform to the target tool's own schema, which is the main thing an agent could get wrong here.

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 uses a specific verb+resource ('Call a Discord tool from a pack by name, with its arguments') and makes the indirection explicit, which is the defining trait of this tool. It also anchors itself against the sibling enable_tools, so an agent can tell this is the dispatch/escape-hatch tool rather than a direct action tool. It stops short of a 5 because 'pack' is never defined and the scope of what tools exist is left open.

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 gives a concrete triggering condition: use it when enable_tools turned a pack on but the new tools are not visible in this app. That is a real when-to-use rule tied to a named sibling. There is no when-not guidance (e.g. prefer calling the tool directly when it is visible), which keeps it below a 5.

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