razz-mcp

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

With no annotations provided, the description carries the full burden of behavioral disclosure but fails to deliver. It omits critical details: message batch size/limit, sort order (newest vs. oldest), whether deleted messages are included, or rate limiting. 'Read' implies safe access, but without annotations confirming read-only status or idempotency, the description should explicitly state these properties.

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?

The description is a single, efficient sentence with the operative verb ('Read') front-loaded. While extremely brief, there is no wasted language or redundancy. However, given the lack of annotations and output schema, the appropriate length for completeness would require additional sentences.

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?

The description is inadequate for a history-retrieval tool with no output schema and no annotations. It fails to describe the return structure, pagination behavior (essential for history endpoints), or message formatting. For a tool handling potentially large message histories, the 6-word description leaves significant gaps that structured fields do not cover.

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 peerId and before parameters fully documented in the schema. The description adds no additional semantic context (e.g., timestamp format examples for 'before,' or whether peerId accepts usernames vs. UUIDs), meeting the baseline expectation when schema coverage is high.

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 clearly states the action ('Read') and resource ('message history with a specific user'), identifying this as a retrieval operation for direct messages. It implicitly distinguishes from siblings like razz_read_dm_conversations (likely a conversation list) by focusing on 'history with a specific user,' though it could explicitly mention 'direct message' to clarify the scope versus general messages or threads.

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?

No guidance is provided on when to use this versus alternatives like razz_read_dm_conversations or razz_read_thread. There is no mention of prerequisites (e.g., whether a conversation must exist first) or pagination strategy guidance, despite the 'before' parameter implying cursor-based pagination.

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