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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds the useful recovery-after-timeout framing, but the word "recover" sits uneasily against readOnlyHint — it does not clarify whether the call merely replays the attempt's state or resumes it, and says nothing about what happens when no attempt is found.

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, zero filler, with the core action first and the usage trigger second. Nothing could be cut without losing meaning.

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?

For a single-parameter, non-destructive read with full annotations, the description covers purpose, trigger and the anti-double-payment rationale. With no output schema, it could usefully say what the recovered attempt returns (status, payment reference), which is the main remaining gap.

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?

One parameter at 0% schema description coverage, so the schema gives only a regex pattern and maxLength. The description does add ownership semantics ("one of the buyer's own orders"), which tells the agent the order_id must be the caller's own, but it never mentions the parameter or any format expectations.

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 ("Read back ... the original delegated payment attempt") plus scope ("for one of the buyer's own orders"). The contrast with paying again implicitly separates it from the sibling evuun_delegated_pay, but the sibling is never named, and the dual verb phrase "read back, and recover" leaves the primary action slightly ambiguous.

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 an explicit trigger ("after a timeout or bank verification") and an explicit alternative to avoid ("instead of paying again"). It stops short of naming evuun_delegated_pay as the tool being replaced, and states no when-not conditions (e.g., no prior attempt exists).

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