List changes

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

Annotations already declare readOnlyHint=true, so safety is covered; the description adds genuinely new behavior: results are ordered newest first, only changes made through discord-mcp are included, and each entry reports what it did plus whether it has been undone. That last point is important context an agent would otherwise have to discover empirically. It stops short of disclosing pagination behavior beyond the limit cap or how far back the history extends.

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 resource and ordering, followed by the enumeration of covered change types and the undo_change linkage. Every clause contributes a fact the agent needs (scope, ordering, entry contents, id purpose) with no filler or repetition of 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 two-optional-parameter read-only tool with no output schema and full schema coverage, the description supplies enough to call it correctly and interpret the results. The main residual gap is pagination/history depth: the agent knows limit caps at 50 but not whether older changes require another call or a different mechanism.

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 100%, with both parameters (guild, limit) fully documented in the schema including the default guild fallback and the default limit of 10. The description adds only the loose phrase 'on a server', which does not meaningfully extend the guild parameter's semantics. Baseline 3 is appropriate when the schema carries the parameter burden.

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 states a specific resource (recent changes made through discord-mcp on a server) with an explicit ordering (newest first) and enumerates the change categories covered: channel/role creates, edits, deletes, permission edits, role grants/revocations, server settings. This clearly separates it from the state-oriented list_* siblings (list_channels, list_roles), which return current configuration rather than a change history. The verb is implied rather than stated outright, which keeps it just below a 5.

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 a clear usage context by naming undo_change and explaining that 'the change_id is what undo_change takes', which tells the agent this is the discovery step preceding an undo. However, there is no explicit when-not guidance (e.g., that it only covers changes made through this MCP server and not changes made directly in the Discord client), leaving the exclusion to be inferred from the phrase 'made through discord-mcp'.

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