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

Adds substantial behavior beyond the annotations: idempotency ('safe to repeat and safe after a different starter'), non-destructive merge semantics ('metrics the workspace already has are left as they are'), and a possible `needs_confirmation` return. This is exactly the beyond-annotation disclosure the dimension rewards.

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-loads the core action, then scope, then idempotency, then next-step guidance. Dense but every clause carries information; only slightly crowded by the interleaved user-facing instruction.

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, so the mention of `needs_confirmation` is doing useful work, and the idempotency/empty-start caveats cover the main surprises. Missing coverage of `approvalId` and workspace scoping keeps it from a 5.

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 75%, so the schema already documents `slugs` and `starter`. The description restates the slug-subset behavior but adds nothing on `approvalId` or `workspace`, both of which stay undocumented in the description. Baseline 3 fits when the schema carries most of the load.

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+resource ('Creates a starter's metrics at their levels and links them') with the linking behavior included, which distinguishes it from a plain metric-create tool. An agent can tell what it does without opening the schema.

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 clear operating context: 'Adopt only what the user agreed to', `slugs` to subset, and follow-up steps (connect a source or a first reading). It stops short of explicitly naming ledger_metric_presets_adopt as the alternative adopt path, so routing between the two adopt tools is left to inference.

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