discord_roles

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the description's silence on safety is not fatal, but it adds nothing either: it never says which of the enumerated actions are destructive, whether the bot needs Manage Roles permission, or that the reason field is the audit-log entry. For a tool exposing delete and reorder this is thin, though it does not contradict the annotations.

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?

Three short sentences, resource first, action list second, escalation path last – nothing redundant. It is terse rather than padded; the brevity is a limitation of substance, not of structure.

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 seven actions, nested body/params/query objects, no output schema, and destructive mutations among the actions, the description should carry more weight. Delegating essentially everything to a separate discord_help call leaves an agent unable to determine required route IDs, permissions, or the effect of delete/reorder without a second round trip.

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 83%, so the schema already explains body, files, query, params and reason. The description adds only a pointer to discord_help for 'required IDs, request fields, limits and examples', which duplicates guidance the schema text already contains; baseline 3 applies.

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?

Names the resource (Discord roles) and enumerates the seven actions, which is enough to distinguish it from sibling resource groups like discord_members or discord_permissions. However, the action names are simply copied from the schema enum and no action is described in terms of what it actually does (e.g. what member_counts returns, what reorder changes).

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 only guidance is a meta-instruction to call discord_help with group="roles" before acting; there is no explanation of when to choose this tool over a sibling, no prerequisite/scope conditions, and no caution that some actions mutate server state. The agent learns nothing about selection criteria, only where to go for details.

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