invoke_session

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 does disclose genuinely useful context: the session is isolated with its own context window and its own cost/capability tier. It says nothing about permission/scope limits, concurrency, failure behavior, or that the call can run in the background (that fact only lives in the schema for await_response).

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?

Two sentences, zero waste, front-loaded with the core action and the salient capability (isolated context window) before the secondary cost/tiering rationale.

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?

For a 15-parameter tool with no annotations and no output schema, the description is thin. It never says what comes back (a distilled response plus presumably a session ID), and critically it does not explain the async path — if await_response=false, the agent needs to be pointed at get_task_status, list_sessions, or send_session_message to follow up, and nothing here does that.

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 every one of the 15 parameters is already documented in structured form. The description echoes agent_preset and the fast/balanced/heavy tier enum but adds no semantics beyond the schema, so the 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?

Specific verb and resource: it spawns an isolated specialist agent session with its own context window, model tier, system prompt, and toolset. An agent can tell what it creates, but the description never distinguishes it from the many adjacent siblings (spawn_agent, start_swarm, invoke_sessions_parallel), all of which sound like they spawn agents too.

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 gestures at motivation ('to save cost while multiplying effective context') and mentions presets/tiering, but gives no explicit condition for choosing this over spawn_agent or invoke_sessions_parallel, and no when-not guidance. With five spawning/orchestration siblings, this is the dimension that most needed attention and it is absent.

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