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

Far exceeds the annotations: it discloses the query_timeout failure mode on broad filters with a concrete remedy, the 5000-row cap behind statusCounts with countsComplete:false meaning partial, the retry semantics at processAfter, the full status taxonomy including the distinction between error and warning/skipped, and the two-step SENSITIVE-GATE flow with the exact gate payload shape. Annotations only say readOnly/idempotent; everything operationally risky is explained here.

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?

Front-loaded with purpose, then usage, then return shape, then filters, then the gate — a logical order with no filler sentences. It is a single dense paragraph, though; the status semantics and gate instructions would scan faster as separated clauses, and a few filter details (limit default/max) repeat the schema verbatim.

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?

There is no output schema, so the description must carry the return contract — and it does, listing all 14 fields of each command, the wrapper keys, ordering, and the statusCounts/partial caveat. Combined with the 88% parameter coverage and the explicit project_id fallback path, nothing an agent needs to call this correctly 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?

Schema coverage is already 88%, so the baseline is 3, but the description adds real meaning the schema lacks: the precedence rule that order_id wins over channel_order_id, the empty statusCounts/limit interplay, and the acknowledge_sensitive two-call protocol. The status enum values are also given operational meaning (waiting/running vs done vs failed vs finished without effect) that the bare enum does not convey.

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?

Opens with a specific verb+resource ("List the ORDER COMMANDS of the project") and immediately defines the concept as "the sync steps behind each order", enumerating concrete command codes (insert_order, add_shipment, add_invoice...). This makes it clearly distinguishable from siblings like list_orders or get_order_overview, which the agent can tell apart without opening any 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?

Gives a strong positive use case: "Use this to find which step of an order failed, when and why, e.g. an order that did not reach the shop or a tracking number that did not reach the marketplace." It also routes the agent to list_orders for orderId and list_projects when project_id_required fires. It never states an explicit exclusion (e.g. "use list_orders instead for order-level summaries"), so this falls just short of a 5.

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