active_orders

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

With no annotations, the description carries the full burden, and it does disclose one real behavioral trait: an empty result is a legitimate empty active set, not evidence of missing history. It says nothing about access requirements, refresh semantics, or what state the feed reflects, so for an unannotated tool this is only partially covered.

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?

One compact sentence with the action front-loaded and the caveat second, no filler. It is arguably compressed to the point of being cryptic about the feed's contents, 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?

A zero-parameter read tool needs little scaffolding, and the negative-space caveat is genuinely useful. However, with no output schema and no description of what the feed returns, the agent cannot anticipate the response shape beyond guessing it is a list of active orders.

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?

The tool takes no parameters, so there is nothing the description could add beyond the empty schema; baseline applies. The description correctly implies the call is unfiltered and context-free.

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?

"Read the active tracking feed" gives a specific verb and resource, and the caveat referencing order history and reconciliation implicitly separates it from the order_history and reconcile_checkout siblings. It stops short of stating what an "active tracking feed" actually contains (in-flight orders with status?), so the agent knows the category but not the payload.

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?

The warning that an empty feed is not order history or reconciliation implies this is the wrong tool to consult for past or financial records, which is a partial when-not signal. There is no explicit instruction such as "use order_history for completed orders" naming the alternative to pick instead.

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