List learning proposals

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond that: required scopes (learning:read, luca:read), data sensitivity full_content, workspace override semantics, and the default dismissal filter. 'Does not require idempotency' is slightly confusing given idempotentHint=true, but it reads as a request-semantics note rather than a contradiction.

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?

Purpose and default filter are front-loaded in two short sentences, then operational metadata is grouped compactly below. The scope/sensitivity/operation block is boilerplate but dense and useful; nothing is padded.

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?

No output schema explanation is needed since one exists, and annotations cover safety. Auth scopes, sensitivity, workspace override, and default filtering are all disclosed. The only missing piece is the meaning of the eventTypes filter.

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?

With 67% schema coverage and three params, the schema documents workspaceId/workspaceSlug and the description reinforces the override behavior. The default-filter sentence conveys activeOnly's meaning, but eventTypes is never explained in the description or schema, leaving a real gap. Baseline-appropriate but not additive across the board.

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 ('List what the coach's tests have learned and are proposing they act on') plus ordering ('newest first'). It clearly distinguishes this from the dismiss sibling (luca_learning_proposals_dismiss), though it doesn't name panel/ab_tests alternatives. Purpose is unambiguous for an agent.

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?

The only usage guidance is the default filter behavior ('Dismissed proposals are left out unless you ask for them'), which maps to the activeOnly parameter rather than telling the agent when to choose this tool over luca_learning_panel, luca_learning_ab_tests_list, or luca_analytics_learning_insights. Usage is implied, not stated with alternatives.

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