start_session

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

With no annotations, the description carries the full burden and does well: it discloses that questions are delivered one at a time, that n defaults to 5 and is capped at 20, that the session terminates with a summary, and that the session has a 'done' state driving a loop. It does not cover what happens on re-invocation with an active session, permission requirements, or error modes.

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 primary action and constraint, then the loop in compact arrow notation — no filler sentences. The arrow chain is dense but scannable for an agent that already knows the sibling names.

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 stateful orchestration entry point with no annotations and no output schema, the lifecycle and next-step routing are covered, but two things an agent needs are missing: what start_session returns (a session_id, only inferable from the later call signature) and what user_id means. Adequate but with clear gaps.

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 0%, so the description must compensate. It fully explains n (default 5, max 20), which the bare integer schema does not, but says nothing about user_id or its 'default' value, leaving one of two parameters undocumented.

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 ('Start a lesson of n questions') plus the shape of the session (questions one at a time, ending with a summary). It is clearly a session-initializer, though it never explicitly distinguishes itself from the sibling start_track, which an agent could plausibly confuse it with.

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 an explicit orchestration path: start here, then loop through get_next_question_brief -> write -> save_question -> user answers -> check_answer/record_result until done, naming the exact siblings to call at each step. It lacks exclusions (e.g., when to prefer start_track or review_mistakes instead), so it stops short of a 5.

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