RealMarket Site Check

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

Annotations already declare readOnly, idempotent, non-destructive and open-world. The description adds meaningful behavior beyond that: it only reads public assets, never logs in, submits forms or probes private routes, which tells the agent the scan is safe but limited in coverage. It omits rate limits, runtime expectations and what happens on sites that are not AI-built.

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, both front-loaded with the most decision-relevant information: what is scanned and reported, then the passive-safety constraint. There is no filler or repetition of the title.

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 compensates by enumerating the report categories an agent should expect. Combined with the stated passive scope, an agent can decide and call confidently; only operational details such as timing or failure modes are absent.

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 each parameter carries its own description, so the schema does the heavy lifting. The description adds only indirect meaning: the mention of 'AI model calls made from the browser' hints at what sends_user_data_to_ai feeds into, but the url and language parameters get no elaboration.

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 concrete verb-plus-resource ("Reads the public pages and public JavaScript of a web app") and then enumerates the exact findings it reports, so an agent knows precisely what this produces. The parenthetical list of build platforms (Lovable, Bolt, v0, Replit) further pins the target compared with the email-security and Shopify siblings.

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 gives clear applicability context (apps typically built with AI tools) and a scope boundary via the passive-check statement. It never names the sibling tools or states when to route elsewhere, so there is no explicit exclusion or alternative 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-redundant behavior: it only touches public DNS records and the public home page (access scope, no credentials), and the report is written in Portuguese — a notable output trait no structured field conveys.

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 primary email-authentication purpose, then the website-security purpose, then the access-scope and output-language constraints. Every clause carries information an agent would otherwise have to guess.

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, no-output-schema tool with strong annotations, this covers purpose, access scope and output language. The only gap is that it does not sketch what the report contains or how findings are surfaced, which an agent may want when deciding whether this tool answers its question.

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?

With a single parameter at 100% schema description coverage, the schema already explains that 'url' accepts either 'example.com' or 'https://example.com'. The description adds no further parameter meaning, such as whether a bare domain vs full URL with path changes behavior. Baseline 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?

Uses a specific verb ('Checks') with two clearly enumerated resources: domain email authentication (SPF, DKIM, DMARC, mail servers) and website security (HTTPS, headers, WordPress exposure, Lovable/Supabase). An agent immediately knows the scope. It does not, however, distinguish itself from the sibling check_ai_built_app, which plausibly overlaps on the 'Lovable/Supabase setup' portion.

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 diagnostic intent is implied by the enumerated checks and the note that it reads only public records, so an agent can infer this is a non-invasive audit. But there is no explicit when-to-use, when-not-to-use, or routing statement pointing to check_ai_built_app or diagnose_shopify_store, leaving sibling selection 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, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds that only public pages are touched (implying no auth or credentials needed), but says nothing about latency, rate limiting, or what happens when the URL is not a Shopify store.

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 findings are front-loaded in a single efficient sentence, so the agent learns the payload immediately. The closing clause 'Reads only public pages' repeats the opening 'Reads the public pages' and could be cut without losing 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?

For a simple two-parameter read tool with full schema coverage and complete annotations, the description is nearly sufficient, and enumerating the reported findings compensates for the absence of an output schema. The main gap is undefined behavior for non-Shopify or unreachable URLs.

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%, including the URL format example and the language enum with its default, so the schema does the heavy lifting. The description adds no parameter-level meaning beyond that, which is the expected baseline of 3.

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 uses a specific verb ('Reads the public pages') on a specific resource ('a Shopify store') and enumerates exactly what it reports: social login, wishlist, sold-out product count, and multi-country storefronts. That resource specificity separates it from siblings check_ai_built_app and check_site_email_security without needing to name them.

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 by the purpose: an agent can infer this is the tool for auditing a Shopify storefront. However, there is no explicit when-to-use/when-not-to-use guidance, no statement about non-Shopify sites, and no routing advice relative to the two sibling checkers.

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