record_project_policy_assignment

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

The description adds meaningful behavioral context beyond the annotations by clarifying that the receipt never authorizes downstream actions and is only a pre-outcome log. However, it doesn't explain what happens when confirm_record is false (e.g., preview vs no-op), which is a minor transparency gap.

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 sentences, front-loaded with the primary purpose, followed by a usage condition and a caveat. There is no filler, and the backticked parameter plus short sentence breaks make it scannable.

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 zero schema descriptions, the description covers the core concept and the confirm flag but leaves the JSON payload formats and several required parameters unexplained. The presence of an output schema helps with return values, but an agent would still need domain knowledge to populate all required fields correctly.

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?

The description maps to key parameters: 'action alternatives' suggests actions_json, 'behavior/candidate probabilities' suggests behavior_policy_json and candidate_policies_json, and 'decision-time source' relates to source_event_id/decided_at. With 0% schema description coverage, this is helpful, but 15 parameters exist and most, including project_id, metric_id, direction, chosen_action_id, evidence_refs_json, and links_json, receive no semantic 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 opens with 'Log exact policy propensities before an outcome exists,' which names a specific verb, resource, and timing. It clearly distinguishes this as a pre-outcome logging action, though it doesn't explicitly name sibling tools for differentiation.

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?

It gives a concrete precondition: set confirm_record=true only after checking action alternatives, behavior/candidate probabilities, and decision-time source. It also states a when-not boundary ('never authorizes execution, learning, skill updates, or policy promotion'), though it doesn't point to alternative tools.

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