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

Annotations already mark this as a non-destructive write (readOnlyHint=false, destructiveHint=false), and the description adds substantial context beyond them: it creates a Ledger entry linked to the opportunity, forbids backfilling, auto-attaches readings as evidence, enforces a single expectation, and discloses the possible `needs_confirmation` return plus the supersede-to-revise workflow.

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 dense sentences, front-loaded with the core purpose and the honesty rationale, then workflow and constraints. Every clause carries information, though the density leaves little breathing room and some cross-references (ledger_metrics_list) are embedded mid-sentence.

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 an 8-parameter mutation tool with 88% schema coverage and no output schema, the description covers the return signal (needs_confirmation), the evidence-linking behavior, and the one-per-opportunity rule. It leaves workspace-scoping and the comparator enum semantics to the schema, which is reasonable given the high coverage.

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 88% schema coverage the schema already documents parameters, but the description adds genuine meaning: metricId must be bound with comparator + target for the expectation to be measurable, and readings then flow in as evidence. It also implicitly ties the approvalId flow to the needs_confirmation response.

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 (register/pre-register an experiment's expectation) and frames it as 'the honesty mechanism' with the concrete action 'Creates a Ledger decision entry and links it to the opportunity.' It distinguishes itself from siblings by the one-per-opportunity constraint and the superseding revision path.

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 when-to-use ('write what the experiment is expected to change BEFORE evidence exists', 'never backfill'), a hard constraint ('One expectation per opportunity — revise by superseding in Ledger'), and a conditional path for measurable expectations. It references ledger_metrics_list but does not explicitly contrast with siblings like compass_opportunities_update for non-expectation edits, so it falls just short of explicit alternatives.

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