Ask about your shared mobility or golf cart fleet: vehicles, trips, riders, revenue and repairs. 40+ tools, role-based access, and nothing changes until a person confirms.
Scored across 3 tools
Each tool has a clearly distinct role: enumerate all topics (list_help_topics), search the corpus (search_help), and fetch a specific page by slug (read_help_page). The descriptions even state the intended workflow between them, leaving no realistic chance of misselection.
All three follow a snake_case verb_noun pattern (list_help_topics, read_help_page, search_help), so the convention is predictable. Minor deviation: the nouns differ (topics vs. page) and search_help drops the object noun, which is a small inconsistency rather than a problem.
Three tools is slightly thin but well-matched to a read-only documentation lookup server, where the natural operations are exactly browse, search, and fetch. No tool feels redundant, and nothing obvious is missing from the count itself.
For a public knowledge base with no write operations, the surface is complete: discovery via list_help_topics, retrieval via read_help_page, and lookup via search_help. The descriptions explain how search results feed into read_help_page, so there are no dead ends.
List every page in Axons Mobility's public knowledge base with its slug and a one-line summary — useful to see what is covered before searching.
| Name | Required | Description | Default |
|---|---|---|---|
| audience | No | visitor = someone looking at Axons Mobility as a product (buyers, partners, press); rider = someone using an operator's branded ride app. Omit to search both. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds behavior the annotations don't: it returns slug + one-line summary per page, and 'every page' signals completeness rather than a sampled result set. Pagination/truncation behavior for a full-corpus listing is still unstated.
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: action, resource, return shape, then the intended use. No filler or redundancy.
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 a single optional parameter documented in the schema, full annotation coverage, and no output schema, the description carries what's needed: what the tool returns and when to reach for it. Minor gap is that 'every page' is not reconciled with the audience filter that narrows the 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?
Schema description coverage is 100% and the audience enum is fully explained in the schema (including the 'omit to search both' default). The description never mentions the audience filter at all, so it adds nothing over 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?
Specific verb ('List') plus resource ('every page in Axons Mobility's public knowledge base') plus the returned payload ('slug and a one-line summary'). The trailing clause 'before searching' implicitly separates it from search_help, so an agent can pick it apart from siblings without opening schemas.
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 — browse the full corpus before doing a search — which sequences it correctly relative to search_help. It never names search_help or read_help_page explicitly, nor states exclusions, so it stops short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read one page of Axons Mobility's public knowledge base in full, by its slug (for example 'visitors/pricing' or 'riders/paying-and-wallet'). Slugs come from search_help and list_help_topics.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The page's slug, e.g. 'visitors/pricing'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds that the page is returned 'in full' (no truncation/pagination), which is genuinely useful, but says nothing about rate limits, auth, or error behavior for a missing slug.
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 tight sentences with zero filler; the core action and key are front-loaded, and the provenance of slugs follows immediately. Nothing 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 single-parameter read tool with full annotation coverage and no output schema, the description supplies everything needed: what is fetched, how it is keyed, where keys come from, and that the content is returned whole.
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 slug parameter, its length bounds, and an example are already documented in the schema. The description repeats the slug concept and adds path-style examples ('visitors/pricing'), which is marginal value over the schema, so the 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?
States a specific verb (read), a specific resource (one page of Axons Mobility's public knowledge base), and the retrieval key (slug), with concrete slug examples. It also distinguishes itself from siblings by naming search_help and list_help_topics as the sources of slugs.
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 makes the workflow explicit: slugs come from search_help and list_help_topics, implying this tool is used after discovery rather than for browsing. It stops short of an explicit when-not-to-use statement, but the routing context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Axons Mobility's public knowledge base. Axons Mobility is software for shared mobility operators (e-scooter, e-bike, moped and car sharing) and golf cart rental businesses: an operator console, a branded rider app, Intelligence, an AI assistant and MCP access. Covers pricing, the free trial and going live, supported vehicles and IoT devices, integrations, safety checks, payments, security and privacy, use cases, and how riders sign up, unlock, ride, pay and get support in an operator's app. Ask in plain words. The best match comes back in full; other matches as an excerpt you can open with read_help_page.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many pages to return. Default 3. | |
| audience | No | visitor = someone looking at Axons Mobility as a product (buyers, partners, press); rider = someone using an operator's branded ride app. Omit to search both. | |
| question | Yes | The question in plain words, e.g. 'how much does it cost' or 'how do I end my ride'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and closed-world behavior, so safety is covered. The description adds genuinely useful behavior beyond that: the best match is returned in full while other matches come back as excerpts, which is important since there is no output 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?
The operative instructions are front-loaded well, but the middle sentence is a long marketing-style enumeration of the product and its feature areas that is closer to domain padding than call-critical information. Every part is defensible, yet the description is noticeably longer than needed to select and invoke the tool.
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 usefully discloses the return shape (full best match plus openable excerpts) and covers the audience distinction and topical scope. An agent has enough to call it correctly; only the lack of guidance on browsing alternatives leaves a small 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 question, audience, and limit are all already documented with examples, enum meanings, and defaults. The description only echoes the plain-words guidance for the question parameter and adds no syntax or format detail beyond the schema, so the 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?
States a specific verb ('Search') and resource ('Axons Mobility's public knowledge base') and enumerates the topical coverage, so an agent knows exactly what corpus is behind it. It also names the sibling read_help_page and the relationship between them, which distinguishes it from list_help_topics without opening a 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?
'Ask in plain words' tells the agent how to phrase input, and quoting read_help_page as the way to open excerpts establishes a clear follow-up workflow. It lacks an explicit when-not clause or a pointer to list_help_topics for browsing, so it is clear context rather than full routing guidance.
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.
list_help_topicsread_help_pagesearch_help
Add one secure layer between your agents and this server.