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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description contributes behavior beyond that: it specifies the read is scoped to one agent's single conversation and, with no output schema, enumerates what the response actually contains — the key thing an agent cannot infer elsewhere.

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?

Front-loaded with the verb and resource, with the id-provenance instruction placed last where it belongs. It is a single dense run-on sentence with deep parentheticals, but every clause names an actual returned field or a routing alternative, so little 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 no output schema, the description carries the return-value burden and does so broadly — covering contact, channel, status, last message, read state, flags, AI state, assignee, and attribution provenance. Coverage of the response is solid; only minor gaps (identifiers/timestamps, message-history pointer) remain.

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% and both parameters already document their 404/403 failure modes. The description adds only one semantic hint — that conversation_id comes from list_conversations — which is marginal over the schema, so baseline 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?

States a specific verb and resource ('Get one conversation of an agent') and then enumerates the exact payload: contact/channel, status, last message, read state, urgent/needs-attention flags, AI state, assignment, and attribution. It also names the sibling that supplies the id (list_conversations), so an agent can distinguish it from list_conversations and list_conversation_messages without opening schemas.

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?

Gives clear entry conditions and routes to alternatives: 'Get its id from list_conversations' and points at list_conversation_ai_switches for who switched the AI and why. It stops short of explicit exclusions (e.g., use list_conversation_messages for the message history), so it is strong context rather than a complete when/when-not rule set.

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