Smoke Run

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description is not carrying the safety burden. It still adds real operational context the annotations lack: it reads account history and therefore requires a Smoke Run API key, and it returns an empty result when no check exists for the site. It stops short of describing rate limits or what the findings payload contains beyond 'dollar-proof'.

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?

Three short sentences, front-loaded with the return value and followed by the auth requirement and the empty-state edge case; each sentence carries distinct information. 'Reads an account history, so it needs a Smoke Run API key' is slightly indirect phrasing for the auth requirement but remains efficient.

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 one-parameter read tool with annotations present and no output schema, the description covers what is returned, the auth prerequisite, and the no-data case, which is enough for correct invocation. The remaining gap is the shape of the findings payload, which the agent only learns at call time.

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%, so siteUrl is already documented with type, format example, and length bound; baseline 3 applies. The description reinforces that the parameter selects a single site's history but adds no syntax, normalization, or validation detail beyond the schema.

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 names a specific verb and resource (returns the most recent revenue-path check) plus the scope (for a given site) and the payload (dollar-proof findings). It implicitly distinguishes itself from list_checks and run_revenue_check by emphasizing 'most recent' and 'read', but it never names those siblings, so an agent must infer the boundary.

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 is implied rather than stated: 'most recent' suggests retrieval of existing results rather than triggering a new check, which points away from run_revenue_check, and the single-site scope points away from list_checks. There is no explicit when-to-use, when-not-to-use, or named alternative, and no prerequisite ordering (e.g., run a check first) beyond the empty-result note.

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?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds context beyond them: the operation is free, keyless, and scoped to publicly reachable pages, plus a hint about a free daily limit being liftable via api_key (in the schema). It does not describe output shape beyond "funnel map," but that is largely the annotations' remaining gap rather than a contradiction.

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, front-loaded with the capability and immediately followed by value/return information. The closing clause about nodes noting what a connected check can verify is slightly abstract but earns its place by signaling the funnel map's cross-references.

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 burden of explaining what comes back, and it does so at a high level (a funnel map whose nodes link to verifiable checks). Combined with the schema's rate-limit note, an agent has enough to call this correctly, though the exact shape of the returned map remains unspecified.

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%, including the url example and the api_key rate-limit explanation, so the schema does the heavy lifting. The description adds only that the target must be a public site, which is useful but marginal beyond the schema.

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 concrete verb ("detects") and a well-scoped resource (the revenue stack / funnel map of a public site), and enumerates the detection categories (payment processor, CRM, email, booking, analytics, ad pixels). It stops short of naming which sibling to use instead, so it is clear but not sibling-differentiating.

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 and needs no key" gives a cost/auth signal that helps an agent decide whether to call it, and the url-based input implies the use case. But there is no explicit when-to-use versus run_revenue_check or get_latest_findings, so the routing decision is left to inference.

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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds ordering (newest first) and account scoping, which is useful, but says nothing about how many results are returned by default, how the limit truncates history, or what a "check" record contains.

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 short sentences, zero filler, with the ordering and scope front-loaded and the optional narrowing called out second. Nothing is redundant or buried.

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 zero-required-parameter, read-only list tool with full schema coverage and no output schema, the description covers what the tool returns at a high level (recent checks, newest first) and how to narrow it. The main remaining gap is that with no output schema it could hint at the shape of a returned check record.

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%, so both limit and siteUrl are already documented in the schema. The description restates siteUrl's filtering role without adding format, matching behavior, or default-value details beyond what the schema provides, 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?

"Lists recent revenue-path checks for the authenticated account, newest first" gives a specific verb (lists), a specific resource (revenue-path checks), the scope (authenticated account) and the ordering (newest first). It is clear on its own, but it never names or contrasts itself with siblings like run_revenue_check or get_latest_findings.

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 is only implied: an agent can infer this retrieves existing checks rather than executing one (run_revenue_check), but the description never states when to choose it over get_latest_findings or get_money_system. No exclusions, prerequisites, or alternative routing are given.

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?

Beyond the readOnlyHint/openWorldHint annotations, it discloses what actually happens during execution: it loads the site as a visitor, walks the landing-to-checkout money path, and never submits a form or completes a charge. It also explains the confidence taxonomy (confirmed / likely / unverifiable) and the constraint that dollar figures attach only to confirmed or likely findings — exactly the behavioral context an agent needs before invoking an open-world crawler.

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 core operation is front-loaded in the first sentence and the confidence-label explanation is placed before the dollar-figure caveat that depends on it. Five sentences for a free-text-only schema is on the longer side, but each carries distinct information; only the 'Free and needs no key' clause mildly overlaps the schema's api_key note.

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 describing the returned report, its finding structure, the confidence labels, and how dollar estimates are scoped. Combined with the safety caveats, an agent knows what it gets back and what the tool will not do, so nothing material is missing for a 2-parameter open-world tool.

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 both parameters are already documented, including that api_key 'is not required for a single check'. The description's 'Free and needs no key' reinforces that but adds no syntax, format or validation meaning beyond the schema, 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?

The description names a specific verb and resource: a read-only, outside-in 'revenue-path teardown of a public website' that returns a 'dollar-proof report'. That is far more specific than a tautology and clearly separates it from read-style siblings like get_latest_findings or list_checks, though it never names those siblings explicitly.

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 establishes useful preconditions ('Free and needs no key', runs 'from outside'), which implies this is the tool to reach for when you need a fresh assessment rather than a stored result. It never states when to prefer get_latest_findings, get_money_system or list_checks instead, so the routing decision is left to inference.

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