Search and read National Digital's website, see pricing and estimate a project.
Scored across 5 tools
Most tools have clearly distinct purposes: search finds pages, fetch reads a page, submit_enquiry sends a message, and get_pricing_and_services returns published pricing. The only mild overlap is between estimate_project and get_pricing_and_services, but their descriptions distinguish a calculated project estimate from indicative published ranges.
All names use snake_case and begin with clear action verbs. The pattern is mostly verb_noun (estimate_project, get_pricing_and_services, submit_enquiry) with a couple of single-verb names (fetch, search) that are natural for generic read operations.
Five tools is well-scoped for a company website assistant focused on discovery, reading, pricing, estimation, and contact. Each tool earns its place without redundancy.
The surface covers the core workflows: search, fetch page content, retrieve pricing/services, estimate project cost, and submit an enquiry. Minor gaps include no direct list-all-pages or explicit contact-details tool, though search can serve as a workaround.
Estimate the cost range for a specific software project. Uses the same calculation as the estimator on the website, so the answer matches what a person would be shown.
| Name | Required | Description | Default |
|---|---|---|---|
| scale | No | Roughly how many people will use it? | |
| audience | No | Who will use it? | |
| timeline | No | When does it need to be live? | |
| projectType | Yes | What are you building? | |
| integrations | No | What does it need to talk to? | |
| newOrReplacement | No | Is this new, or replacing something? |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false. The description adds a useful guarantee that results match the website estimator, but does not disclose auth requirements, rate limits, or the precise shape of the returned range.
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, front-loaded with the core action and followed by a useful consistency guarantee. No filler, though the second sentence is a nice-to-have rather than essential.
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 estimation tool with fully documented params and annotations covering safety, the description is largely complete. The lack of an output schema means the description only vaguely signals that a cost range is returned, which is a minor gap.
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 six parameters with enums and plain-language prompts. The description adds no additional parameter semantics, 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 opens with a specific verb and resource: 'Estimate the cost range for a specific software project.' It distinguishes the tool as an estimator that mirrors the website estimator. It does not explicitly contrast itself with siblings like get_pricing_and_services or submit_enquiry.
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?
There is no statement of when to use this tool versus the alternatives. The reader can infer it produces a cost estimate, but nothing addresses prerequisites or when get_pricing_and_services would be preferred over it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read one published National Digital page as clean Markdown, given an id from search (the page's site path, e.g. /platform-engineering/) or its full URL. Returns the page's text with its title, canonical url and last-modified date. Long pages are returned in parts; pass the returned nextOffset as offset to read the next part.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | A page id from search (its site path, e.g. /about/) or the page URL. | |
| offset | No | Character offset to read from; pass nextOffset from the previous part. |
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| url | Yes | |
| text | Yes | |
| title | Yes | |
| metadata | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: content is returned as Markdown with title, canonical url and last-modified, and long pages are chunked with a nextOffset/offset continuation contract. It does not mention error cases (e.g. page not found or unpublished), which keeps it at 4.
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, front-loaded with the core action, then the return shape, then the pagination loop. No filler or redundancy; each sentence carries 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?
Covers the inputs, the source of ids, the return payload, and the pagination continuation rule; an output schema exists so return values needn't be spelled out further. For a two-parameter read tool, nothing an agent needs in order to call it 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% and both parameters are documented in the schema, including the offset/nextOffset relationship and the id example. The description restates rather than extends that: it gives the same site-path-vs-URL distinction and the same offset chaining rule, adding no new syntax or edge-case meaning.
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 (read) and resource (one published National Digital page) plus output format (clean Markdown), and distinguishes itself from the sibling `search` by noting the id comes from search. An agent can identify the tool 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?
Explains that the id comes from `search` and that either a site path (/platform-engineering/) or a full URL is acceptable, which implies the intended workflow (search first, then fetch). It does not state explicit exclusions or what to do if the id is unknown, 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.
What National Digital builds and supports, and what each kind of project typically costs, in AUD. Includes the Product Support retainer for ongoing engineering on production platforms, including platforms built by other teams, and the standard hourly rate card for work outside a retainer. Ranges are indicative and come from delivered work; they are not quotes. Returns an empty list when no pricing has been published, rather than an estimate.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description correctly spends its words elsewhere: the provenance of the ranges, the non-quote disclaimer, and the important edge case that an empty list is returned when no pricing is published instead of an estimate. That empty-result behavior is a genuine operational detail beyond the structured fields.
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 scope is front-loaded in the first clause, followed by the retainer/rate-card detail and the disclaimer. Three sentences is slightly more than strictly needed, but each carries information the agent cannot get from the schema or annotations.
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 parameters, no output schema, and annotations already declaring the safety profile, the description supplies exactly what is missing: what is returned, the currency, the reliability caveat, and the empty-list behavior. Nothing needed to call it correctly is 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?
The tool takes zero parameters, so there are no semantics to document and the baseline is 4. The description does not waste space restating an empty schema, which 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 states a specific resource and scope: what the company builds and supports plus typical project costs in AUD, including the support retainer and hourly rate card. It implicitly contrasts with the sibling estimate_project by insisting the figures are delivered-work ranges, 'not quotes,' so an agent can tell these two apart.
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: the agent can infer this is for retrieving published pricing and that it should not be treated as a quote-generating tool. It never explicitly says when to call this versus estimate_project, nor names that sibling, so the routing 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.
Search National Digital's published pages - services, articles, case studies and pricing - for a topic or keyword. Returns up to 10 ranked results, each with an id, title, url, type and a short excerpt. Pass a result's id to fetch for the page's full text.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Limit results to one kind of page: Pillar (a service area), Hub (a service), Leaf (an in-depth guide), CaseStudy (a client project) or Static (company pages such as /about/ and /services/). | |
| limit | No | Results to return; default 8. | |
| query | Yes | Words describing the topic, service or question. |
| Name | Required | Description |
|---|---|---|
| results | Yes |
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 usefully adds the result ceiling ('up to 10 ranked results') and the per-result field shape, which 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?
Three tight sentences, front-loaded with what is searched, then scope, then return shape, then the handoff to fetch. 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?
Output schema exists and annotations cover the safety profile, so the description need not enumerate return fields exhaustively. It supplies everything an agent needs: scope, result count, and the follow-up 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%, including a fully documented enum and default for limit, so the schema carries the parameter burden. The description only restates query as a topic/keyword search and adds no format or syntax guidance 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 specific verb (Search) plus resource (National Digital's published pages) and enumerates the content types covered. It is clearly separable from siblings like fetch, since it explicitly notes that fetch is the follow-up step for full text.
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 ('for a topic or keyword') and an explicit next-step handoff ('Pass a result's id to fetch'). It does not state when to prefer a sibling such as get_pricing_and_services for pricing content, so it stops short of full alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send an enquiry to National Digital on behalf of the person you are helping. Only use this when they have asked you to make contact. A human replies within one business day.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | The enquirer's name. | |
| Yes | A work email address to reply to. | ||
| company | No | Their organisation. | |
| message | Yes | What they are trying to do, in their own words where possible. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), so the description's job is added context. It contributes two useful facts beyond the annotations: the message reaches an external human, and a reply arrives within one business day. It does not mention that repeated calls could generate duplicate enquiries despite non-idempotency, which would have been worth stating.
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, zero filler, with the action statement front-loaded and the usage constraint immediately after. The response-expectation sentence is short and earns its place by setting the user's expectation.
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 four-parameter outbound message tool with fully documented params, no nested objects, and no output schema, the description covers action, consent gating, and turnaround. The only meaningful omission is that it never warns the agent that a second call creates a second enquiry, which matters given idempotentHint=false.
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 all four parameters (name, email, company, message) are already documented in the schema. The description adds no syntax, format, or content guidance for any parameter, so the baseline 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?
States a specific verb and resource ('Send an enquiry to National Digital') and adds the acting-on-behalf-of framing, which tells the agent this is an outbound communication on a user's behalf rather than a data lookup. It does not explicitly contrast itself with the siblings (estimate_project, fetch, get_pricing_and_services, search), but the action is distinct enough that confusion is unlikely.
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 an explicit gating condition: 'Only use this when they have asked you to make contact.' That is both a when-to-use and a when-not-to-use statement, which is exactly what an agent needs before firing off an outbound message. No alternative tool is named because none of the siblings is a substitute for this action.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
fetch2 fields changedOutput schema / properties / metadata / properties / nextOffset / anyOfRemoved value: -[
- {
- "type": "number"
- },
- {
- "type": "null"
- }
-]Output schema / properties / metadata / properties / nextOffset / typeAdded value: +[
+ "number",
+ "null"
+]estimate_projectfetchget_pricing_and_servicessearchsubmit_enquirySearch Accent's public website and get non-binding budgetary estimates from published plan prices.
Scans any public website for SEO, AI search, trust, conversion and speed, and lists our prices.
Audit a site's structured data and llms.txt, match a trade to a template, and quote real prices.
Free preflight and exact-price discovery for paid website and AI-agent audits.
Add one secure layer between your agents and this server.
