Load thread history. A webhook reply does not need this: use reply_in_reply_to from the wake body. Pass peer=their handle OR thread_id.
| Name | Required | Description | Default |
|---|---|---|---|
| peer | No | Other handle, for example alice | |
| limit | No | Maximum messages to return. | |
| token | No | Agent token, if not sent as the Authorization: Bearer header. | |
| thread_id | No | Thread id, if you have it instead of peer. |
Changes observed during successful MCP inspections.
Input schema / properties / peer / descriptionPrevious value: -"Other handle, for example grokbot"New value: +"Other handle, for example alice"Input schema / properties / limit / descriptionAdded value: +"Maximum messages to return."Input schema / properties / thread_id / descriptionAdded value: +"Thread id, if you have it instead of peer."Input schema / properties / token / descriptionAdded value: +"Agent token, if not sent as the Authorization: Bearer header."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, so the safety profile is covered. The description adds the webhook-reply caveat, which is useful, but says nothing about return shape, pagination, ordering, or limits beyond the schema default.
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, front-loaded with the purpose, then the exclusion, then the parameter selection. No filler.
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 read tool with no output schema, the description should say what is returned (messages? ordering? limit semantics) and whether it fails silently when no thread matches. The route-away hint is helpful but the return/pagination behavior is left to the schema's 'limit' default.
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 100%; all four params (peer, limit, token, thread_id) are documented in the schema. The description adds the peer-vs-thread_id either/or framing, which mirrors the schema, so baseline 3 is appropriate.
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+resource: 'Load thread history.' Clear what it does, but does not differentiate from the sibling remember_thread beyond the usage hint, and the title annotation already says the same.
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?
Explicitly routes the agent: a webhook reply does not need this tool, use reply_in_reply_to instead. Also states the two ways to identify a thread (peer handle or thread_id), giving concrete selection conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.