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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower, yet the description adds genuinely new context: the 'held' state carries a hold status and expiry, and the untrusted_text warning tells the agent how to treat broker/hook/person-supplied data. That prompt-injection guidance is behavioral information no annotation or schema conveys.

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?

Two sentences, tightly front-loaded: the resource and the identifier come first, the status enumeration and the when-to-use rule follow, and the injection warning closes it out. Nothing is redundant or padded.

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 carries the return-value burden and does so by enumerating the possible statuses and noting the held sub-fields, while the input side is fully covered by the schema. For a one-parameter read tool, an agent has everything it needs to call it and interpret the result.

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 100% and there is a single parameter, so the schema already documents idempotency_key. The description confirms provenance ('the idempotency_key the trading tool returned'), which mirrors rather than extends the schema field description, so baseline 3 applies.

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?

The description states a precise retrieval (what happened to a sent trade) keyed on the exact identifier the trading tool returned, and enumerates the full result space (in_flight, held, applied, rejected, no_change, unknown). That keying on idempotency_key cleanly separates it from siblings like get_orders and get_history, which the agent could otherwise conflate with it.

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?

It gives an explicit triggering condition ('after an unknown or held result') and names the behavior to avoid ('instead of resending'), which is effectively the alternative it competes with. It stops short of pointing at a sibling tool or stating a positive when-not-to-use case (e.g. before you have an idempotency_key), so it is clear context rather than a complete routing rule.

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