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

Annotations only assert idempotentHint/destructiveHint; the description goes well beyond them by explaining retry safety (same opId does nothing twice), the stale-version conflict rule (older basePlanVersion still applies unless the item changed, otherwise item_changed_in_current_version with no mutation), and that 'complete' means a human checked the shot, not technical quality. This is exactly the mutation/conflict context an agent needs before writing.

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?

The core action leads, followed by the op payload contract, retry/conflict semantics, and identifier rules, so it is front-loaded and every sentence carries information. It is dense and telegraphic, and the identifier/visibility details could be split more cleanly, but there is no filler.

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 batched idempotent mutation with a nested op array and repeated parameters, the description covers payload construction, idempotency, version conflict outcomes, identifier sourcing, and access scoping. With an output schema present it does not need to describe return shapes, and it already names the partial-failure result string.

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%, so the description carries the full burden and does: it defines opId as a fresh random UUID v4, basePlanVersion as the plan's current version, itemKey syntax, and the state enum values, plus the taskId format rules (full id vs. 8-char prefix vs. orderReference). Only the optional recordedAt field is left undiscussed, which is minor.

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 precise verb pair (tick/untick) and the exact resources affected (shot:<shotId> and check:<itemId> items in a shoot plan), which is far more specific than the title 'Tick off shots'. It references shoot_plan_get and shoot_plan_list as the sources for its inputs, implicitly separating it from those read-only siblings, though it never names a sibling it replaces or rules out.

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: itemKey values come from shoot_plan_get, taskId comes from shoot_plan_list (not planId, with prefix/orderReference alternatives allowed), and the visibility rule for Connections is stated. There is no explicit when-not-to-use or routing against alternatives such as shoot_plan_revise, which is the only gap.

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