commit_assessment

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

With no annotations provided, the description carries the full burden and discloses meaningful behaviors: it is a server-side mutation, raw_answer is stored for audit and never discarded, and mastery_probability is runtime-computed. This is solid for a write tool, though it omits reversibility and the optimistic-concurrency role of expected_state_version.

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, purpose front-loaded, no filler. The second sentence packs three distinct facts (mandatory params, audit retention, runtime computation) into a compact block, which is dense but not disorganized enough to penalize heavily.

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 13-parameter mutation tool with zero schema descriptions, no output schema, and no annotations, the description is under-specified. It explains the core intent and two parameters but leaves ten parameters, their value ranges, concurrency semantics, and the return shape unaddressed. An agent cannot confidently construct a correct call without guessing at most field meanings.

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, but it only adds meaning for two of thirteen parameters. Worse, it introduces a discrepancy: it calls assessor_type 'mandatory' while the schema gives it a default and only attempt_id/raw_answer are required, and it references mastery_probability, which is absent from the schema entirely. The remaining ten parameters (transfer, confidence, correctness, reasoning_quality, etc.) receive no explanation.

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 a specific verb (commit) and resource (assessment evidence), and discloses a side effect (update learner state server-side). This distinguishes it from evaluation tools like assess_response and generation tools like generate_assessment, though it doesn't explicitly name a sibling, and the boundary with submit_attempt is left implicit.

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?

No when-to-use guidance or exclusions are provided. The description implies this is the persistence step after assessment, but it never names alternatives (submit_attempt, assess_response, commit_pedagogical_decision) or states the condition that selects this tool over them. The mandatory-parameter note reads as parameter guidance rather than usage context.

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