Update daily draft

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the write produces an immutable revision (history is preserved) and is gated on the current version. It does not say what happens on a version mismatch (error vs. retry), nor whether the prior revision is superseded.

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?

Two tight sentences with the core action front-loaded and zero filler. The compression slightly costs clarity — 'checking the current version' is a vague way to describe optimistic-concurrency enforcement — but 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?

For an 8-required-parameter mutation with 0% schema coverage and a conflict-sensitive version parameter, the description is far too thin: no conflict/failure behavior, no explanation of the provenance fields, no routing against the five sibling draft tools. The output schema being present removes the need to describe returns, but the input and behavioral gaps dominate.

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 description coverage is 0% across 8 required parameters, and the description compensates for only one: the status enum, where it explains REJECTED vs. PENDING semantics. draftId, expectedVersion, sourceEventIds, sourceFingerprint, summary, workItems, and nextActions carry no meaning in the description; provenance fields like sourceFingerprint are left entirely unexplained by both schema and text.

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 states a concrete action (create a new immutable revision) and explains the version-check precondition, which clarifies that this is an append-only revision of a draft rather than an in-place edit. It never names a sibling, so the agent cannot tell from the description alone how this differs from save_daily_draft or approve_daily_draft.

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?

'After checking the current version' hints at a read-then-write flow, but there is no explicit when-to-use guidance and no exclusion relative to save_daily_draft, approve_daily_draft, or list/get_daily_draft. The only guidance given ('Use REJECTED to reject and PENDING to edit or reopen') is about the status value, not about tool selection.

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