JustAutomate website

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, not open-world), but the description adds meaningful behavior: the server never submits forms, books meetings or sends messages, and the agent must relay contact details to the user. This goes beyond the annotations by defining the interaction contract, though return format is not described.

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 what the tool provides and followed by the key constraint. The clause about not submitting forms/bookings/sending messages is slightly redundant with readOnlyHint but is the most actionable part, so it earns its place.

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-optional-parameter read tool with no output schema, the description conveys what the agent gets (contact channels and a booking option) and how to use it. Nothing critical is missing, though it does not state the exact shape of returned links or addresses.

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 lang parameter already documents its enum values. The description's mention of Polish, English or German mirrors that enum, adding only human-readable framing rather than new semantics, so the standard 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 resource (contact channels: e-mail, phone, contact form) and the outcome (how to reach JustAutomate or book a free consultation), which clearly separates it from siblings like get_page, search_site and get_workshop_offer. An agent can identify the tool's role 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 gives clear operational context — pass the link or address to the user and let them decide — and rules out the server acting on the user's behalf. It does not explicitly name when to prefer this over get_page or search_site, so it stops short of full when/when-not 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, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond them: the output is sanitized Markdown with front matter, redirects to current addresses are followed, and a defined set of pages is inaccessible. It does not mention rate limits or error/404 behavior, so a 4 rather than 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?

Three sentences, each carrying distinct information (what is returned, accepted input forms plus redirect handling, availability limits), with the core purpose front-loaded. Zero 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?

With no output schema, the description compensates by describing the return shape (Markdown plus front matter fields) and, with full schema coverage on the single parameter, it states accepted input formats and exclusions. An agent has everything needed 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% and there is only one parameter, so the baseline is 3. The description adds genuine meaning beyond the schema: concrete accepted path formats ('/uslugi/', '/en/services/process-workshop/') and the fact that outdated URLs are resolved to their current page.

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 and resource ('Return the content of one public page of justautomate.ai') and even specifies the representation ('as clean Markdown, no navigation, scripts or forms, with title, description and canonical URL in the front matter'). This is clearly distinguishable from siblings like list_pages or search_site, which enumerate rather than fetch a single page.

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 input context (full URL or path like '/uslugi/'), notes that old addresses redirect to their current page, and states an explicit exclusion ('Private client offers and pages excluded from search engines are not available'). It does not explicitly contrast with the sibling tools (e.g., when to prefer search_site or list_pages first), so it stops short of full when/when-not 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 readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely new behavioral context beyond them: prices are net and exclude VAT, the value is per week, and implementation pricing is deliberately withheld until after the workshop — a business constraint an agent could not infer.

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 key payload (what is returned) is buried after an opening sentence of engagement-process framing that does not help an agent invoke the tool. The second sentence is dense but well organized, so the paragraph is padded rather than wasteful.

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 describing returns and does so explicitly (price, duration, deliverables, offer page). Nothing critical is missing for a single-optional-param read tool, though VAT/currency treatment could be stated neutrally rather than in prose.

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 enum is documented, so the baseline is 3. The description goes further by annotating each market with its currency (PL→PLN, CH→CHF, INTL→EUR) and clarifying that omitting the market returns all of them, which adds meaning beyond the bare enum list.

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 resource (the process workshop offer) and enumerates exactly what is returned: net price per week, duration, deliverables, and an offer page per market. It is unmistakable against the siblings (get_contact_options, get_page, list_pages, search_site), none of which touch workshop pricing.

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: framing the workshop as 'how every JustAutomate engagement starts' and noting that implementation is quoted only after the workshop hints at when this tool applies. No explicit when-to-use, no named alternative, and no conditions telling the agent when to pick a sibling tool instead.

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 readOnly, idempotent, non-destructive behavior, so the bar is lower; the description nonetheless adds a genuinely non-obvious trait: ~1,400 near-identical city pages are hidden unless type="city", which prevents an agent from being surprised by results or bloating output. It does not mention pagination defaults or result ordering.

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 tightly written sentences, front-loaded with the core action and filters, with the important city-page caveat placed last as a qualifier. No 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 read-only paginated list tool with a fully documented schema and no output schema, the description covers filters, pagination, and the one non-obvious behavioral trap. Return shape and pagination defaults are left to the schema/annotations, which is acceptable.

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 beyond the schema by explaining that the 'city' type value gates access to a special population of pages, which the enum alone does not convey. The lang and limit/offset params remain schema-only.

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 ('List public pages of justautomate.ai') plus its scope (public, paginated), which clearly separates it from the singular get_page sibling. It stops short of explicitly naming alternatives like search_site, so it is clear but not fully differentiated.

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 tells the agent the tool can be filtered by kind and language and supports pagination, implying usage, but gives no explicit 'use this instead of search_site when...' guidance or prerequisites. Usage is inferred 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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds value beyond them by disclosing the return shape ('titles, descriptions and URLs') and the public/unauthenticated access model, which the annotations alone do not 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?

Two sentences, both front-loaded: capability and scope first, follow-up action second. The regional/vertical elaboration is compact and serves selection rather than padding.

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 supplies the essential return shape and the get_page handoff, and the schema covers all four parameters. Minor gaps remain — result ranking/relevance behavior and whether limit is the only paging control — but nothing blocks a correct call.

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% with per-parameter descriptions and enums, so the schema carries the semantics. The description's 'in Polish, English and German' and the enumerated content kinds loosely mirror the lang/type enums but add no syntax or matching-behavior detail beyond it, making 3 the appropriate 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+resource ('Search the public website of JustAutomate') and scopes it precisely: which site, which regions, which content kinds, which languages. It also distinguishes itself from the read-side sibling by naming get_page as the follow-up step, so an agent can separate search from read 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 clear context (public site search) and an explicit next-step alternative — 'read a result with get_page' — which routes the agent correctly after results come back. It does not, however, contrast with list_pages or get_workshop_offer, so the agent must infer when browsing/enumeration is preferable to keyword search.

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