gc_conversation

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

No annotations are provided, so the description carries the full burden. It lists actions but doesn't disclose important behaviors: whether turn is stateful across calls, what happens on session errors, rate limits, or whether sessions persist across agent executions. The 'backend-neutral' note adds some transparency value. Without annotations, the behavioral disclosure is thin but the action list does convey the core operations reasonably.

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 reasonably compact given the tool's complexity (10 actions). The action list with short inline annotations is front-loaded and scannable. Each action gets a brief descriptor. It's not bloated, though the bullet format could be slightly tighter given the schema already defines each action in the enum.

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 12 params, 1 enum (10 actions), no output schema, and no annotations, this is a high-complexity tool. The description covers the action catalog well but lacks depth on workflows (e.g., the spawn→turn→submit_tool_results→turn cycle, which appears to be a multi-step interaction pattern). It also doesn't clarify return/session semantics. Given the complexity and absence of annotations and output schema, this is adequate but 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%, so every parameter has a description. The description adds value by indicating which parameters apply to which action (e.g., 'persona/agent_name, optional config, make_apex' for spawn, 'send a message' for turn). It also clarifies aliases (id for session_id, agent/agent_name for persona, results for tool_results). This mapping of parameters to specific actions is genuinely helpful 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 states this handles 'Interactive AI conversation sessions' and enumerates actions (spawn, turn, submit_tool_results, cut_in, etc.). However, this is a multi-action dispatcher tool where the actual purpose depends on which action is chosen, and the description reads more like a menu than a concise statement of a single purpose. It's clear about scope (backend-neutral, inferring it abstracts across providers) but doesn't sharply distinguish it from the many conversation sibling tools (gc_agent_conversation, gc_peer_conversation, gc_aden).

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 action list implies usage contexts (e.g., 'turn: send a message and get the assistant response'), but there's no explicit guidance on when to use gc_conversation versus alternatives like gc_agent_conversation or gc_peer_conversation. The 'backend-neutral' framing hints at generality but doesn't state exclusions or which sibling to prefer in what circumstances. No when-not-to-use guidance is given.

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