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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false) by disclosing the irreversible, write-once nature ('cannot move afterward'), the side effect of attaching to the linked Ledger entry as evidence, and the possible `needs_confirmation` response with its approvalId loop.

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?

Five dense sentences that are front-loaded with the trigger and the boundary meaning. The opening label 'The measurement window's boundary:' is slightly abstract, but every sentence carries distinct information and nothing is wasted.

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?

With no output schema, the description still covers the mutation's effect, its permanence, the confirmation/approval flow, and the evidence attachment, which is everything an agent needs to invoke it correctly against a 5-param, 100%-covered schema.

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 100%, so the baseline is 3, but the description adds conceptual meaning to `at` (baseline before, effect evidence after) and ties `approvalId` to the needs_confirmation flow that is not spelled out in the annotated description alone.

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: recording the date the experiment's change shipped, framed as the measurement window boundary. This is clearly distinguishable from sibling mutations like compass_opportunities_set_status, update, or register_expectation.

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 an explicit trigger ('when the user says the experiment's change actually shipped / went live / rolled out') and a confirmation precondition ('Recorded once — it cannot move afterward, so confirm the date'). It does not name or exclude specific sibling tools, but the when-to-use condition is unmistakable.

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