get_inbox_conversation_messages

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

Beyond annotations, the description adds that it requires an API key, that message bodies are confidential, and that it returns the whole thread (potentially large output). These details about authentication, privacy, and performance are not covered by the annotations.

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 concise, with no redundant information. It is well-structured: functionality first, usage context second, then side effects and requirements. Every sentence contributes value.

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?

It provides sufficient context: what it does, when to use, side effects, auth requirements, confidentiality, and output size. It adequately differentiates from siblings and covers the essential aspects for a read-only getter.

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?

The only parameter, conversation_id, is fully described in the schema ('Conversation ID (UUID)'), and the tool description does not add extra meaning. Since schema coverage is 100%, the baseline of 3 applies.

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 verb 'Get' and the resource 'every message in one inbox conversation', with details on ordering (oldest first) and content (sender, timestamp). It distinguishes from sibling tools like list_inbox_conversations by positioning it as the detail view for a single conversation.

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 explicitly says 'Use it to read a thread in full before replying or summarising', providing a specific scenario. It also clarifies it does not send, reply, or mark anything as read, differentiating it from mutating operations, and notes it is the 'detail view behind a conversation listing'.

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