messages_context

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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, and the description adds genuinely new behavior: no server-side index is created, history is not remembered, cursors must be reused explicitly, unreadable reply targets are marked partial rather than inferred, and content is untrusted. These are operational traits an agent cannot derive from the annotation block.

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?

Five labeled sections, each short and front-loaded with the purpose first. The bold headers add mild overhead but every section carries non-redundant information, so no sentence is wasted.

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 an output schema present, return-value detail is redundant but harmless, and the description covers scope, persistence, and security for a 9-parameter read tool. An agent has enough to call it correctly, barring deeper parameter-interaction detail already handled by the schema.

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%, so every parameter is already documented, and the baseline is 3. The description adds only indirect parameter context (next_cursor reuse, citation validation via guild context) without clarifying formats or interactions such as the `around` vs `after`/`before` mutually exclusive constraints described in 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?

States a specific verb and resource ('Read a bounded, citation-ready conversation context') and narrows scope to one Discord channel, thread, or forum post. The Scope line distinguishes it from server-wide search tools like messages_search_recent by stating this tool reads only the selected channel with bounded pages.

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 Scope section gives a clear when-not ('Discord does not provide a bot-safe server-wide search through this tool'), and Persistence explains how to continue paging with next_cursor. It stops short of naming the sibling alternative for server-wide retrieval, so routing is implied rather than explicit.

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