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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds real behavioral context beyond them — link lifetime of 30 minutes, the pending-vs-submitted distinction with hash presence, and an explicit polling throttle. It does not cover auth requirements or what happens to an approval after the link expires.

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?

A single dense sentence front-loads the core purpose (status of an approval) before the status enumeration and the get_order handoff. Every clause carries information, though the parenthetical status list makes it slightly harder to scan than a short lede plus a follow-up sentence would be.

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?

With no output schema, the description compensates by spelling out the possible return states and the correct next tool for each, which is the key information an agent needs. Missing only peripheral items such as auth/permission requirements and post-expiry behavior.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents that `id` is the apr_… value returned by place_*/cancel_order. The description adds no syntax, format, or edge-case semantics beyond that, so the baseline 3 is appropriate.

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 specific verb+resource ('Status of an approval you created') and enumerates the full set of possible outcomes (pending, submitted, rejected, failed, expired). It also routes the agent to the sibling get_order once an orderHash/txHash exists, so it is distinguishable from check_order and get_order 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?

Gives explicit follow-up routing ('then use get_order to follow fills') and a polling cadence constraint ('Poll no more than every few seconds'), which tells the agent how to behave after calling. It stops short of stating when this tool should not be used or which sibling to prefer when the approval is already submitted/failed.

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