route_learning_task

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

With no annotations, the description carries the full burden, and it does real work: it declares read-only semantics and enumerates four things it will not do (log in, start playback, save answers, submit). It also clarifies the output is a plan ('tools and dependencies'), 'not a claim that the session is connected' — a subtle but useful disclosure about what the result does and does not guarantee.

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?

Three short lines with the router role front-loaded, followed by output semantics and exclusions. Every sentence carries information; the phrasing 'not a claim that the session is connected' is slightly oblique but is doing real work about return-value interpretation.

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?

An output schema exists, so return structure need not be described. What is missing is the operational follow-through: whether the returned 'tools and dependencies' should then be invoked in order, and how the transport parameter interacts with the routing. For a top-level router over 120 tools, that gap matters.

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 0% with two enum parameters, so the description must compensate. It gives selection guidance for task_type ('from user intent and observed task type') but calls it 'mode', never matching the schema field name, and it says nothing at all about 'transport' (browser vs cdp), a choice that plausibly changes execution behavior.

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 identifies a specific function — a 'unified read-only entry point' that routes to a mode based on 'user intent and observed task type' — which is meaningful differentiation against a ~120-tool sibling list where most tools are concrete actions. It falls short of 5 because the routed resource is never named concretely (the task types exist only in the schema enum), so the agent must open the schema to learn what it routes among.

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?

'Unified read-only entry point' implies this should be called before the concrete action tools, and the negative list ('does not log in, start playback, save answers, or submit anything') implies when not to expect it to act. However, it never explicitly states whether to call this before or instead of siblings like inspect_course, prepare_course_quiz, or start_learning_batch, which is the central routing decision for an agent.

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