Smartsheet Audit (x402)

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds value beyond that: it discloses that results are truncated to the top 3 issue types and that the call is rate-limited, both of which affect how an agent should plan repeated calls.

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 sentence with the value proposition front-loaded ('Free preview') followed by the returned fields and the constraint. Every clause carries information; no filler or restatement of the tool name.

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?

There is no output schema, and the description compensates by listing the returned fields. For a single-parameter read-only tool with a fully documented nested schema, this is nearly complete; it only omits how the preview relates to the full audit and any detail on the rate limit.

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 nested 'sheet' object is documented in the schema itself (exact API endpoint, required columns/rows, optional shares and automationRules, token warning). The description adds nothing further about the parameter, so the baseline of 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?

States a specific resource (Smartsheet workflow audit) and enumerates the concrete output (score, grade, issue counts, top 3 issue types), so the agent knows exactly what comes back. It signals it is a lighter-weight variant ('preview', 'top 3') but never names the sibling audit_smartsheet, so differentiation is left to inference.

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?

'Free preview' and 'Rate-limited' imply this is a cheap first pass before the full audit, which is usable guidance. However, the description never explicitly says when to use this instead of audit_smartsheet, nor what happens after previewing, so the agent must infer the workflow.

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

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

The description goes well beyond the annotations by disclosing the paid-operation mechanics: $0.10 USDC on eip155:8453, the payTo address, and that an unpaid call returns x402 payment requirements instead of an audit. That is genuinely useful context the annotations do not carry. It still omits failure modes on malformed sheet JSON and any rate limits, so it is not fully transparent.

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 capability summary is front-loaded as a compact noun list, followed by the return contract and then the payment terms — a sensible order. The single long enumeration sentence is dense but every item earns its place by telling the agent what the audit covers.

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 a single nested parameter, 100% schema coverage, and annotations declaring readOnly/openWorld=false, the description fills the remaining gaps: output content and the notable payment/fallback behavior that would otherwise surprise an agent. Only minor gaps remain around error handling for malformed input.

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 the nested `sheet` description already specifies the exact source endpoint, required fields (columns, rows), optional additions (shares, automationRules), and the token-safety rule. The description adds no parameter-level meaning beyond that, so the 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?

Names a specific verb+resource ("Smartsheet workflow audit") and enumerates exactly what is inspected: formulas, column types, hierarchy/predecessors, duplicates, blanks, size, sharing, automation risks. It also states the output shape (score, findings with severity + fix, markdown report). It does not distinguish itself from the sibling audit_preview, so it stops short of a 5.

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?

Usage context is implied by the enumerated check list, and the description does clarify the payment precondition and the unpaid fallback path. However, it gives no guidance on when to choose this over the sibling audit_preview, nor any prerequisites about sheet size or required data.

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