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

Annotations state readOnlyHint=false, destructiveHint=false, openWorldHint=false, but the description adds the crucial behavioral fact that these are non-committing proposals reviewed in Decisions → Drafts, that confidence is low for historical claims, and that the call may return `needs_confirmation`. Those are traits the annotations cannot convey.

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 safety are front-loaded in the first sentence, and the remaining sentences are operational instructions rather than filler. It is dense and fairly long, with some stylistic guidance ('say so plainly rather than overstating them') that is useful but could be tightened.

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 write-of-drafts tool with no output schema, no nested-object flag, and 50% schema coverage, the description supplies the workflow, the history-specific field rules, the confidence caveat, the user-facing next step, and the possible `needs_confirmation` return. Nothing essential for correct invocation is missing.

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 50% schema coverage, the description compensates well: it explains fromHistory semantics, prescribes landedAt ('when it shipped'), rollout defaults ('full unless the source says otherwise'), source URL attachment, and that prediction is decisions-only. It doesn't touch workspace or approvalId, but the high-value parameters are covered.

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 a specific verb, resource, and scope: 'Writes up to 50 entries as DRAFTS: proposals that stay out of the record until a person confirms each one in Ledger's Drafts view.' The 'draft' framing distinguishes it cleanly from ledger_entries_create, which commits records, so an agent can route without opening a 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?

It explicitly states when to use it ('entries you found rather than were told') and gives concrete trigger examples — decisions in meeting notes, a team's past changes from its tracker, PRs, or launch posts — plus the fromHistory condition. This is explicit when-to-use guidance with no inference required.

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