SeoAiX SEO Audit

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

With no annotations, the description carries the full burden. It discloses the ~7 signals checked, the return type (weighted 0–100 score + top fixes), and the limitation that it returns a summary only (full report via email). It doesn't explicitly state the audit is read-only or mention URL accessibility requirements, but 'Audit ANY URL' implies a non-mutating operation; a small transparency gap remains.

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 description is front-loaded with the primary purpose and scope, then follows a logical flow: signals checked, output format, parameter, sibling routing, and report escalation. Every sentence contributes distinct information, with no redundancy or filler.

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, read-only audit with no output schema or annotations, the description covers everything an agent needs: what it does, what inputs it takes, what it returns, which siblings to use instead, and how to get the complete report. No critical operational detail is missing.

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% (url described with 'The website URL to audit, e.g. https://example.com'), so baseline is 3. The description adds 'ANY URL' and the contrast with get_my_store_audit, clarifying that the parameter accepts arbitrary public URLs, not just connected stores. This goes slightly 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 states a specific verb and resource ('Audit ANY URL') with a precise scope ('AI-search readiness only (AEO/GEO/LLMO)'), clearly differentiating it from full SEO audits. It enumerates concrete signals checked and the output (0–100 score + top fixes), leaving no ambiguity about what the tool does.

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?

Explicitly names alternatives with conditions: 'Use full_seo_audit for the broader SEO picture, or get_my_store_audit for the user's own connected store.' Also routes to email_seo_report for the full written report, informing the agent when this tool suffices and when a sibling is more appropriate.

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?

With no annotations, the description carries the full burden and does it well: it flags that approving can change the live store, that the first call is side-effect free and returns a preview plus a confirmToken, that the token is valid 10 minutes and single-use, and that an "approve" permission scope is required. These are exactly the mutation-safety facts an agent cannot get from the schema.

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?

Front-loaded with the action and its blast radius ("Approving can change the live store"), then the two-call protocol, then the safety rules, then the permission requirement. Every sentence carries an instruction the agent needs; nothing is padding despite the length.

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 four-parameter, no-output-schema mutation tool, everything needed to call it correctly is present: id provenance, the two-step confirmToken handshake, the human-approval requirement, the batch prohibition, and the auth scope. No output schema exists, and the description already tells the agent what the first call returns.

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 75%, so the schema already documents id, api_key, and confirmToken. The description still adds real meaning beyond it: confirmToken must be the one from the preview, sent on the second call along with the same arguments. It says nothing extra about api_key, which the schema already handles, so this is above baseline without being exhaustive.

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 pair (approve or reject) against a precisely scoped resource: exactly ONE pending SeoAiX recommendation, for the user's own store. It also names the sibling that supplies the ids (list_pending_approvals), so the agent can distinguish it from every other sibling in the list.

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 explicit when-to-use (after picking one id from list_pending_approvals), explicit how (two calls, first without confirmToken), and explicit exclusions (never confirm on your own judgement, never loop over many items). The human-approval gate and the permission prerequisite are both stated as conditions, not 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?

With no annotations provided, the description carries the full behavioral burden. It discloses the critical consent rule ('never guess or reuse an address'), the weekly re-audit behavior when weekly is true, and the one-click unsubscribe property. This gives the agent the safety-relevant context needed to invoke the tool appropriately.

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 description is overly repetitive. 'Email the full written SEO/AEO report for an audit this session already ran' largely duplicates the first sentence, 'ONLY use an email address the user explicitly gave you' repeats the earlier consent warning, and 'Offer this after presenting audit results' restates 'ALWAYS OFFER THIS after running an audit.' The content is good but could be condensed to roughly half its length.

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 three-parameter tool with no output schema and no annotations, this description is complete. It explains when to use it, where the audit_id comes from, how to handle the email address, and what weekly mode does. The agent has enough information to call the tool correctly and safely.

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 the baseline is 3. The description adds value by explicitly tying audit_id to the outputs of ai_search_diagnostic or full_seo_audit, and by reinforcing that email must be explicitly supplied by the user rather than guessed. This helps the agent understand parameter provenance 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 clearly identifies the tool's purpose: email the complete written SEO/AEO report for an audit run earlier in the session. It also distinguishes this from the audit tools by noting they return a summary of top issues while this sends every check, evidence, and fix in priority order.

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?

The description gives explicit when-to-use guidance: 'ALWAYS OFFER THIS after running an audit' and 'Offer this after presenting audit results.' It also specifies the source of audit_id (ai_search_diagnostic or full_seo_audit) and instructs the agent to ask for and use only the user's explicitly provided email, which is important operational guidance.

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?

No annotations are provided, so the description carries the full burden. It discloses that the tool crawls the URL, requires no login, returns a weighted 0–100 score plus top issues, and returns only a summary while the full report goes via email. It does not mention rate limits or robots.txt compliance, which keeps it just short of a 5.

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 description is long but densely informative: each clause names a concrete SEO area, and the sibling-tool distinction is front-loaded near the end. No filler words appear, though the first sentence is quite packed and could be split for easier parsing.

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?

Despite having only one parameter and no output schema, the description fully covers input format, audit scope, output type, authentication expectation ('no login needed'), alternatives, and where the complete report is delivered. The agent has enough context 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 description coverage is 100%: the `url` property already explains it is the website URL with an example. The description merely repeats 'Takes a `url`' and adds 'ANY URL', which adds only marginal clarification. Baseline 3 is appropriate since the schema already handles parameter documentation.

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 opens with a specific action ('Crawl-audit'), a clearly defined target ('ANY URL'), and a bounded scope ('the WHOLE SEO surface'), then enumerates the covered areas: AI-search signals, on-page SEO, technical SEO, and Shopify schema. It distinguishes itself from get_my_store_audit, so the agent knows exactly what this tool is and is not.

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 explicitly states when to use this tool ('ANY URL', 'arbitrary website', 'no login needed') and names the alternative for a different case: 'for the user's OWN connected store with real analytics, use get_my_store_audit.' It also mentions email_seo_report for the full written report, giving clear routing context.

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?

With no annotations, the description carries the full burden and does well: it discloses the input sources it reads (home page, robots.txt, sitemap, sample key pages), the output structure, that copy is drawn from the site's own titles/meta descriptions rather than AI rewriting, and that it also reports existing /llms.txt presence. It omits failure behavior for unreachable or bot-blocked sites and any latency/rate expectations.

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?

Purpose is front-loaded in the first clause, and the middle sentences carry genuinely useful behavioral detail rather than filler. It is slightly overpacked into one paragraph and repeats the publish-at-root instruction, minor waste in an otherwise dense definition.

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 tool with no output schema and no annotations, the description explains the return shape (title, one-line summary, `## Section` link lists) and the source material, so an agent knows what to expect. Edge cases such as invalid URLs, timeouts, or sites without a sitemap are unaddressed.

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 the single `url` parameter is already fully documented with an example. The description only adds "Takes a `url`" plus the notion that it may be any website, which is marginal beyond the schema; 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 opens with a specific verb+resource ("Generate an llms.txt file (llmstxt.org format)") and scopes it to "ANY website". Neither sibling tool (audits, diagnostics, SEO reports) produces an llms.txt, so the agent can distinguish it immediately without opening the schema.

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 states clear eligibility context — works on any website and requires no login — and sets an expectation that output should be reviewed before publishing at the site root. It does not name alternatives or say when NOT to use it (e.g., sites blocking bots), which keeps it below a 5.

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?

With no annotations, the description carries the full behavioral burden and does disclose the auth model (API key required, accepted either as an Authorization: Bearer header or the api_key argument) and the data source it reads from. It does not say what happens if no store is connected, whether the call is read-only, or any rate-limit/error behavior, leaving some gaps.

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 claim (your own connected store's deep in-app audit) is front-loaded, and the auth/prerequisite details follow. The long em-dash parenthetical listing the 12 categories and the 'far beyond what crawling a URL can see' clause are somewhat dense but still earn their place by establishing scope.

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?

No output schema or annotations exist, so the description must stand alone; it covers purpose, scope, data source and auth setup, which is nearly everything needed to call it. It omits the failure mode when no store is connected and any indication of the response shape beyond the category list.

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?

Only one optional parameter and schema description coverage is 100%, so the schema already documents api_key fully; the description restates the same header-vs-argument alternative. Baseline for a near-zero-parameter tool is 4, and nothing extra is added.

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 ('Get the user's OWN connected Shopify store audit') and pins the scope to a 12-category in-app report using the store's real catalog, performance and analytics. It also implicitly distinguishes itself from a URL-crawl audit, so an agent can tell it apart from siblings like full_seo_audit.

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 clear usage context: it 'takes no url', so it is the right choice only for a connected store, and it names the prerequisites (SeoAiX API key plus a connected store). It stops short of explicitly naming a sibling tool as the alternative for URL-based audits, so 4 rather than 5.

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?

No annotations, so the description carries full burden. It discloses the comparison windows, default period, and the exact metric families returned, and 'get' implies read-only, but it says nothing about prerequisites (connected GSC/GA4/Merchant accounts), what happens when data is missing, or auth expectations beyond what the schema already states.

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 front-loaded sentence that leads with the core behavior and then enumerates metrics; no filler. It is dense and somewhat list-heavy, but every clause conveys actionable information.

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 and no annotations, the description must define the return payload, and it does list the metric groups. It is incomplete on edge cases — unavailable data sources, permission/plan requirements, and result shape — which matter for a multi-source aggregated report.

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 supplies the one missing semantic — that `days` defaults to 7 — which the schema's enum does not express. The api_key parameter is already documented in the schema, so no compensation is needed there.

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+resource: reports period-over-period movement for the user's own store across named metrics (audit score, GSC, GA4, Merchant Center). Scope is narrowed to 'the user's own store', which distinguishes it from broader reporting siblings, though no sibling is named 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?

Usage is only implied by 'versus the period before' — an agent can infer this is for trend/delta analysis, but there is no explicit when-to-use, when-not, or pointer to alternatives like get_weekly_report or get_my_store_audit that also surface store performance.

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?

No annotations are provided, so the description carries the burden of behavioral disclosure. It usefully states the authentication requirement and lists the kinds of status information returned, but it does not explicitly confirm read-only behavior, describe permissions beyond the API key, or explain response format or rate limits.

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 description is a single front-loaded sentence that lists the relevant status areas without obvious filler. It is appropriately sized for the tool, though the conversational opening and long inline list are slightly less structured than an ideal definition.

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 simple read-oriented status tool with one optional parameter and no output schema or annotations, the description gives a useful inventory of what the status covers and the required authentication context. It could be more complete by clarifying read-only behavior and how the status differs from sibling tools, but the core information needed to invoke it is present.

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 the api_key parameter is already documented in the schema, including that it can be supplied via Authorization: Bearer header. The description reinforces that a store-bound SeoAiX API key is needed but adds no syntax or additional parameter meaning 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 clearly identifies the resource as the user's own connected SeoAiX store and enumerates the status areas covered: Search Console / GA4 / Merchant Center connection and sync state, content plan, indexing coverage, pending merchant items, and diagnostic notes. This is specific enough to distinguish a status check from siblings like get_my_store_audit or get_recent_changes, though it does not explicitly name those alternatives.

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?

The phrase 'right now' and the emphasis on the user's OWN connected store imply a current-state inspection use case, but the description does not explicitly state when to use this tool versus get_my_store_audit, get_recent_changes, or get_weekly_report. Usage is inferable but not guided.

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?

No annotations exist, so the description carries the full burden. It does disclose the returned content, which is valuable given there is no output schema, and 'the user's own store' implies scope limiting. However it says nothing about failure modes (no report generated for that week), whether the read is idempotent/side-effect free, or auth requirements beyond what the schema already documents.

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 front-loaded sentence with the resource and payload enumerated, followed by the one parameter clarification. No filler, no restatement of the tool name, and the parameter note is placed after the purpose.

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 correctly enumerates what comes back, and it covers the optional historical-week parameter. The remaining gap is behavior when the requested week has no report or when `week_start` is omitted (presumably current week), which is left implicit.

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%, so the baseline is 3, but the description adds real meaning the schema lacks: `week_start` is specifically the Monday that a past report covers, not an arbitrary date. That is a semantic constraint (day-of-week alignment, past-only) an agent would otherwise get wrong from the schema's bare 'e.g. 2026-10-26'.

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+resource ('this week's SeoAiX report for the user's own store') and enumerates the payload (traffic, revenue, keyword changes, actions taken, narrative, priorities), which clearly separates it from siblings like full_seo_audit or get_store_status. It does not explicitly name an alternative, so it stops just 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?

The mention that `week_start` retrieves 'a past report' implies the when-to-use condition (default = current week, provide a date = historical), but there is no explicit routing guidance versus email_seo_report (which presumably sends rather than returns the report) or get_recent_changes. Usage is inferable rather than stated.

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?

With no annotations, the description shoulders the behavioral burden. It adds significant value by stating the ordering criteria ('escalated ones first, with what to check') and naming the specific IDs returned by the tool that map directly to subsequent API 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?

The description is highly efficient, packing a broad scope and technical details into two sentences. While the first sentence is slightly dense, the information density justifies the score.

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?

Given there is no output schema, the description provides comprehensive guidance on what the user will receive—namely, IDs mapped to specific action tools. This makes the tool highly actionable for an agent.

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?

Since the input schema coverage is 100% and the tool only requires a single optional parameter, the description adds no semantic value or further detail beyond what the structured schema already provides. The baseline score of 3 is appropriate.

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 clearly defines its role as a tracking tool for pending tasks. It precisely names the resources (recommendations and drafts) and explicitly differentiates its function from the execution tools, specifically naming 'decide_recommendation' and 'publish_draft' as downstream actions.

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?

The description provides clear context for when to use the tool (when the merchant needs to see their outstanding approvals or drafts). However, it does not provide prescriptive guidance on the workflow or when to choose this tool over other listing/audit tools.

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?

With no annotations provided, the description carries the full behavioral burden and does so well. It discloses that the first call changes nothing, the second publishes live, the confirmToken is valid for 10 minutes and single-use, and an approve-permission key is required.

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 description is front-loaded with the core purpose and then lays out the two-step protocol and constraints. Every sentence contributes operational guidance, with no redundant filler.

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?

Given a three-parameter mutation tool with no annotations and no output schema, the description covers the essential call sequence, safety checks, token behavior, and permission needs. It provides enough context for an agent to invoke the tool correctly without needing further structured metadata.

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%, so the baseline is 3. The description adds useful meaning beyond the schema by explaining the confirmToken lifecycle and the permission requirement tied to api_key, though it does not detail every parameter nuance.

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 verb and resource: publish one ready article draft live on the user's Shopify store. It also identifies the source of the id via list_pending_approvals, making it clearly distinguishable from sibling tools.

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 explicitly defines the two-call workflow: first without confirmToken to preview, then only after clear user approval with the token. It also rules out autonomous confirmation and looping over many items, leaving no ambiguity about when and how to use the tool.

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?

With no annotations, the description carries the full burden and does substantial work: it discloses pricing ($19/mo with free trial), that the call returns a personalised signup link rather than completing anything, and that payment and store connection finish in the browser. It also names the upstream data sources read and the write actions the subscription performs (publishing articles, fixing meta/alt-text). It stops short of stating auth prerequisites, idempotency on repeat calls, or what the link expires to.

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, front-loaded paragraph: purpose first, then what the product does, pricing, return value, and finally the parameter caveat. The parenthetical feature inventory is dense and partly promotional, but it doubles as behavioural disclosure rather than pure filler.

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?

No output schema exists, and the description compensates by explaining the return (a personalised signup link) and where the flow continues. Pricing, trial, and both optional parameters are covered; only preconditions such as required account state or repeat-call behaviour are left open.

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%, so the baseline is 3, but the description adds a genuinely useful operating constraint beyond the schema: pass email/store_url ONLY if the user explicitly provided them and never invent either. That is the kind of anti-hallucination guidance the schema hints at but does not enforce as strongly.

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 action and product ("Start an SeoAiX subscription") and immediately scopes what that subscription does, so an agent can tell it apart from the sibling diagnostic/audit/report tools without inspecting any schema. The verb+resource pairing is unambiguous.

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?

The description implies the trigger (a user wanting the paid product) and gives a firm rule for the parameters, but never states when NOT to use this tool or which sibling to reach for instead (e.g. a free audit via full_seo_audit or ai_search_diagnostic). Usage is inferable rather than explicit.

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