configure

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

Annotations only declare readOnlyHint=false, so the description carries most of the burden and does well by disclosing apply-time semantics: most settings take effect immediately, while tool groups, read-only mode, and status require an app restart. That restart split is exactly the kind of behavior an agent needs before promising a change took effect, though it says nothing about partial-update semantics for unspecified settings.

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 sentences, front-loaded with the invocation condition and then the persistence/restart caveat, with no filler. The colon-and-list construction in the first sentence is slightly dense but still readable.

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 10-parameter mutation tool with no output schema and only a single annotation, the description covers when to call, what is configurable, and restart timing. It omits the important question of whether omitted parameters are left unchanged versus reset, and it does not surface the dry_run safety path, both of which matter for a local-config mutation.

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 60%, and the description's setting list roughly maps to write_mode, allowed_servers, tool_groups, confirm_permanent_actions, default_server, and status. It adds real meaning for tool_groups, write_mode, and status via the restart note, but online, status_text, status_type, and dry_run get no mention in the description, leaving the gap to the schema.

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 names a specific verb and resource: change this Discord tool's own settings and persist them locally, then enumerates the setting categories (write mode, allowed servers, tool packs, confirmation, default server, bot status). That scope ('this tool's own settings on this computer') separates it from server-level siblings like edit_server or enable_tools. It stops short of a crisp one-line purpose statement, but the intent is unambiguous.

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 opens with an explicit gating condition, 'Only when the user asks: change this Discord tool's own settings', which tells the agent both when to call it and when not to. No alternative or fallback tool is named, so the routing is clear but not fully closed.

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