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

Annotations only declare readOnlyHint=true, but the description discloses the full state machine, the terminal nature of three states, that an 'executed' result rides this response, and the non-obvious exception that approved invoice_share/quote_share stores no link (pointing to result.link_not_stored.next_call). These are exactly the behavioral traits annotations cannot express.

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 critical fact (what to do on pending) is front-loaded and every clause carries operational meaning. The final executed/link_not_stored clause is a long nested run-on that costs some readability, but nothing is 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?

No output schema exists, so the description carries return-value burden entirely — and it does, enumerating all five states and their downstream consequences including the link-not-stored exception. Nothing an agent needs to call this correctly and handle the result 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 100% and the single property already documents that approval_id comes from the APPROVAL_REQUIRED refusal envelope, so the description largely restates the schema. The 'scoped to the granting user's approvals' clause adds a modest access-scope nuance, keeping it at baseline rather than above.

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 and resource ('Check a parked approval') and pins the identifier's origin ('returned in an APPROVAL_REQUIRED refusal'), which unambiguously separates it from siblings like expense_approve or simpler.invoke. An agent can tell exactly what this does without opening the 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 per-state instructions: pending means tell the user and do NOT retry the original call; executed means never re-run the call; rejected/expired/failed are terminal and only re-composed if the user asks again. That is a complete when/when-not decision table, not mere context.

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