record_project_learning_review

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

The annotations already indicate readOnlyHint=false, destructiveHint=false, and idempotentHint=false. The description adds meaningful behavioral detail beyond that: it creates only a shadow-training observation and never mutates learner, routing, policy, promotion, dispatch, action, or production-write state. This clarifies the exact write surface and guards against the agent expecting broad side effects.

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 compact and front-loaded: the first sentence defines the exact scope, and the second sentence gives the conditional usage rule. Every sentence earns its place, and there is no repeated schema or annotation content.

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?

The core workflow and side-effect boundary are well covered, and an output schema exists to describe return values. But for a 12-parameter tool with 9 required fields and 0% schema coverage, the description leaves receipt-chain mechanics and several parameter meanings unexplained. An agent would likely need to infer too much about mission_run_receipt_id, mission_action_receipt_id, outcome_receipt_id, and evidence_refs_json.

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%, so the description carries the burden. It does add real meaning for confirm_record (gated on human inspection) and for decision (helped/hurt/bad evidence/needs more evidence). However, the other nine required parameters, including the three receipt IDs and skill_trial_arm, are not semantically explained beyond their names, so the compensation is only partial.

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?

Description states a specific verb ('record') and resource ('Human-account Level-Up Review for one exact mission receipt chain'). It further distinguishes the tool by declaring it creates a shadow-training observation only and explicitly names record_skill_outcome as something it never calls. This scoping is precise enough for an agent to separate it from sibling review/record tools.

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?

Explicitly says confirm_record=true should be set 'only after the human has inspected the Mission Debrief' and has chosen among helped, hurt, bad evidence, or needs more evidence. This gives a clear precondition and decision workflow. The statement that it never calls record_skill_outcome or changes live state also tells the agent when this tool is not the right choice.

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