get_conversation

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

With no annotations, the description carries the behavioral transparency burden. It discloses that results are ordered, include both directions, and have reply_text inline, which is meaningful behavioral detail even though it does not explain pagination or limit semantics.

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 tight sentences, with the primary action and return shape front-loaded and the use case in the second sentence. Every sentence earns its place.

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 3-parameter read tool with an output schema present, the description covers purpose, return shape, and when to use it. It is not fully complete because it lacks guidance on pagination (before_id) and explicit differentiation from sibling tools.

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 0%, so the description must compensate. It clarifies partner_bot_id as 'one partner' and the recency/ordering tied to limit, but it never explains before_id's cursor/pagination role, leaving a noticeable gap.

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?

Description opens with a specific verb ('Fetch') and a concrete resource: recent message history between the agent and one partner. It explicitly notes the returned artifact (ordered incoming+outgoing messages with reply_text inline), which separates it from siblings like list_conversations and get_inbox.

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 description gives a clear use case: 'Use to give the LLM conversational context before composing a reply.' It does not enumerate exclusions or compare itself to siblings such as list_conversations or context_for_wake, so it misses the when-not-to-use guidance.

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