212medya Growth Check

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

Annotations already declare readOnly, openWorld and non-destructive, and the description still adds real behavior: it fetches only the given page plus robots.txt and sitemap, honors robots.txt, returns category scores and prioritized fixes in English, and caches results for the same page for up to 6 hours. The performance test's cost is also surfaced as an up-to-30-second addition.

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 trigger and exclusions in the first and last sentences, with scope and caching facts in between. Dense but mostly earning its place; the long mid-sentence feature list is the only slightly run-on element.

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?

Covers trigger, exclusions, fetch scope, robots compliance, latency cost, caching, and output language, and an output schema already documents return structure. Nothing an agent needs in order to call this correctly 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%, so the schema already documents all three parameters, including PageSpeed's 30-second cost and the ISO 639-1 language format. The description echoes these (language versions for export markets, mobile performance via PageSpeed Insights) but adds no syntax or default detail beyond the schema, which is the expected baseline.

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 (marketing audit of a public website) and enumerates the concrete dimensions checked: technical SEO, mobile performance, lead conversion, trust signals, analytics tags, and language versions. It explicitly names the sibling it is not (check_ai_search_readiness), so an agent can route without opening either 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?

Gives a positive trigger ('when the user wants a marketing audit of a public website, especially a B2B, manufacturer, exporter or service-business site') plus three explicit exclusions: AI crawler/search questions, login-gated pages, and monitoring sites the user isn't evaluating. The alternative for the AI case is named directly.

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 readOnlyHint/openWorldHint, the description discloses what the analysis actually inspects, that only the given page plus robots.txt and sitemap are fetched, the shape of the return (scores, crawler access table, prioritized fixes in English), and two explicit coverage limits. These are behavioral facts the annotations cannot convey.

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?

Dense but front-loaded: the trigger condition comes first, then the checks, then the exclusions. The long enumeration of checks is justified because it defines scope, though it could be tightened slightly without loss.

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?

An output schema exists, so return-value explanation is optional, yet the description still sketches the output. Combined with the declared scope, limits, and sibling routing, nothing is missing for an agent to call this tool 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 100% and the single url parameter is already documented with format examples and the 'only this page is analyzed' scope note, so the description adds no new parameter-level meaning. Baseline 3 applies when the schema does the work.

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 condition and resource: checking whether a public website can be crawled, read and cited by named AI assistants and AI search engines. It enumerates the concrete checks (robots.txt per AI crawler, Content-Signal, noindex/nosnippet, JS readability, FAQ, Organization schema/sameAs, sitemap, llms.txt), so an agent can distinguish it from audit_website at a glance.

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 the trigger explicitly (the user asks if AI tools can read/cite the site, or why AI tools don't show the company) and names the alternative for the adjacent case: general SEO or conversion audits belong to audit_website. It also declares two negative boundaries — no brand-mention measurement and no CDN/firewall bot-block testing — so an agent knows when to escalate elsewhere.

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 annotations it discloses the full side-effect chain: details are emailed to the agency team, persisted in a lead database, and answered by a specialist, plus the idempotency warning that every call sends a new request and must not be retried after success. This is exactly the context destructiveHint=true implies but cannot explain; the only gap is that it doesn't say what the tool returns on success or failure.

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?

Seven sentences, all load-bearing: the eligibility gate comes first, then the consent prerequisite, then data handling, then the retry warning, then exclusions. No filler or restatement of the title, and the most important constraint is front-loaded.

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 9-parameter outbound-write tool with annotations and an output schema, the description covers everything an agent needs before calling: who to contact, when it is permitted, what must be shown and confirmed, where the data goes, and that calls are non-idempotent. Return values are covered by the existing output schema.

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 schema already defines every field and its constraints. The description still adds meaning by enumerating the exact data set the user must be shown before sending and flagging website and phone as optional, tying the parameters to a consent workflow rather than just a payload.

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 action (requesting a human expert review) and a specific counterparty (212medya, the agency publishing the app), and explicitly narrows it to cases where the user asks to be contacted. It also implicitly separates it from the sibling audit tools by stating it must not be used to save or share audit results.

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 an explicit gate ('only when the user explicitly asks to be contacted'), a required pre-call workflow (show the exact fields, obtain confirmation), and a negative rule (do not use it to save/share audit results, or when the user only wants information). Alternatives — the audit siblings — are effectively pointed at by the exclusion clause.

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