gc_agent_conversation

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

No annotations are provided, so the description carries full burden. The description lists actions but reveals nothing about behavioral implications: whether deletion is destructive, whether spawning requires a specific agent name, whether turns mutate session state, or rate limits. It describes what actions exist but not the consequences or lifecycle of sessions.

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 compact (two sentences) and the action list is helpful, but the second sentence is largely a restatement of the schema enum and could earn more value. It's appropriately short but the space used could carry more useful behavioral or usage detail.

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 no output schema, no annotations, 7 parameters, nested objects, and 5 distinct actions each with different parameter needs, the description is too thin. The action enum alone doesn't explain which parameters apply to which action, what each action returns, or the session lifecycle. For a multi-action tool this is materially incomplete.

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% with descriptive parameter labels (alias notes for id/agent, 'for spawn' parentheticals on config/agent_name/message). The description simply restates the action enum without adding meaning. Baseline 3 is appropriate since the schema already documents each parameter well, though the description adds no extra semantic value.

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 states 'Chat-style sessions with local GC agents' which gives a clear conceptual domain, and lists the five actions (spawn, turn, get, list, delete). However, it doesn't say what the tool DOES with a specific verb+resource framing that distinguishes it from similar objects like gc_conversation and gc_peer_conversation in the sibling list. The purpose is understandable but the distinction from sibling conversation tools is unclear.

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 provides no guidance on when to use this tool versus gc_conversation, gc_peer_conversation, or gc_sessions. It lists actions but gives no context about selection criteria, prerequisites (e.g., an agent must be spawned before turning), or when not to use it. This is a significant gap given the large sibling set of conversation-related tools.

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