Get Conversation

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

The description discloses that visiting UI rows 'may also mark them as read' (unusual if no read hint provided). It also explains how the UI's restrictions make enumeration necessary, and the side effect makes the agent more informed.

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?

Dense, layered description that explains LinkedIn UI limitations and the match between the index and thread IDs. Each sentence adds information, but it's somewhat lengthy as it packs in all behavior.

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?

Input schema is complete, output schema, openWorldHint, descriptions of parameter semantics, but no mention of errors, permissions, or result shape (output schema fills that). Adequate for given complexity.

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 schema documentation is 100% covered and describes 'index' behavior with 0-based selection and its precedence relationship to thread_id; the description of the lookup parameters adds contextual nuance beyond schema.

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 clear action ('read a specific conversation') and distinguishes it as one conversation by username or ID. Sibling tools like get_inbox list all messages, so the 'specific' scope is evident. It lacks explicit sibling differentiation, but the verb+object is specific.

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?

Explains the linkedin_username lookup path, what it does (enumerating rows), and when to pass thread_id directly 'to skip this enumeration'. It says it's 'the only available path' to justify behavior. No explicit alternatives list, but usage implication is strong.

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