Get Conversation

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

With only openWorldHint in annotations, the description carries the burden of disclosing side effects. It explicitly warns that username-based resolution click-visits matching rows and 'may mark it as read,' which is a non-obvious behavioral trait an agent must know before invoking the tool. It also explains the LinkedIn UI limitation that forces this behavior.

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 sentences, zero filler. The core purpose is front-loaded, and the longer second sentence earns its length by explaining a critical behavioral caveat and its root cause. The final sentence gives a clear escape hatch. No word 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 documentation is already handled. The description covers all invocation paths, parameter interactions, side effects, and a rationale for the unusual behavior. An agent has everything needed to call this tool correctly, including how to avoid the side-effectful path.

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%, so the baseline is 3. The description adds meaningful parameter context: explaining that linkedin_username triggers a UI enumeration process, that index selects among multiple threads, and that thread_id bypasses the enumeration. This goes beyond the schema's dry definitions without being redundant.

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 opens with a specific verb and resource: 'Read a specific messaging conversation.' It then details two unambiguous lookup modes, making it clear this tool targets one conversation rather than inbox-wide operations, which distinguishes it from siblings like get_inbox and search_conversations even without naming them.

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 clear guidance on when to use each input path: pass thread_id to avoid the expensive username enumeration, and use linkedin_username when you don't have a thread_id. It does not explicitly state when to prefer this tool over sibling tools, but the read-specific-conversation scope is strongly implied.

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