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

No annotations are supplied, so the description carries the full behavioral burden, and it does disclose meaningful traits: the price ($0.02 USDC on Solana per op), that payment is required per invocation, and that the result is a signed grade. It does not describe what happens with a malformed or non-promise listing, whether the grade can fail or return an error shape, or what the signed artifact contains. Useful payment/auth context, but incomplete for the zero-annotation bar.

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 with no padding, and every clause carries information. The front-loading of price ahead of the tool's actual function is slightly off-priority, but the comparison pair and 'margin printed' land clearly.

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 paid, nested-object tool with no output schema, the description covers cost, payment rail, what is compared, and that output is signed and includes a margin. It leaves out the shape of the returned grade, the meaning/domain of `op`, and how it relates to the criteria/precheck/check siblings, which an agent needs to invoke it correctly.

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 50%. The description adds meaning for the `listing` object by naming the two graded fields (declared delivery time and maxTimeoutSeconds), reinforcing the schema's promise sub-field list. The `op` parameter remains unexplained in both places beyond the vague 'in the op's published form' and the pricing phrase 'per op', so an agent gets no help knowing what values it accepts.

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 specific operation: it produces one signed promise-consistency grade comparing a listing's declared delivery time against its quoted maxTimeoutSeconds, with margin printed. This is concrete enough to distinguish it from generic checks. It does not, however, explicitly differentiate itself from siblings like listing_check_check, listing_check_criteria or listing_check_precheck, which share the same prefix.

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?

There is no explicit when-to-use or when-not-to-use statement, and no named alternative among the five listing_check_* siblings. Usage is only inferable from the phrase 'the listing's declared delivery time against its quoted maxTimeoutSeconds', which implies this is for promise/latency consistency rather than the other listing checks. With seven sibling tools sharing the prefix, the lack of routing guidance is a real gap.

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