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

The description discloses a non-obvious side effect not captured by annotations: reading a thread marks it seen. This aligns with the non-read-only annotation and gives the agent critical operational context before invoking the tool.

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 front-loaded with what is returned, immediately follows with the side-effect warning, and then routes to alternatives. Every sentence contributes either purpose, caution, or differentiation.

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?

Given two parameters, full schema coverage, no output schema, and a meaningful side effect, the description provides enough context to invoke it correctly. It covers returned contents, the key warning, and sibling-tool boundaries.

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%, so both parameters are already documented in the input schema. The description only lightly echoes the message-history behavior through its mention of full history, without adding parameter-specific syntax or constraints beyond the 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?

The description clearly identifies the resource as one conversation thread and specifies that it returns the full message history, the associated lead, and the originating campaign. It also distinguishes this prospect-facing exchange from sibling tools like agent_logs and lead_get, so an agent can tell what it retrieves without opening the schema.

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 gives an explicit when-not-to-use rule: reading marks the thread seen, so it should not be used merely to browse unless the user wants the badge cleared. It also names the correct alternatives for agent reasoning logs and lead step history, leaving little inference for tool selection.

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