Read-only search and page retrieval from the public Atisbo documentation corpus. No authentication.
Scored across 3 tools
Each tool has a clear, non-overlapping purpose: get_doc retrieves a single page, list_docs enumerates available pages, and search_docs finds pages by query. There is no ambiguity about which tool to use in a given situation.
All three tools follow a uniform verb_noun snake_case pattern: get_doc, list_docs, search_docs. This makes the toolset predictable and easy to learn.
Three tools is well-scoped for a read-only documentation server. Each tool covers a distinct and necessary operation without redundancy or bloat.
The toolset fully covers the documentation browsing workflow: discover pages (list_docs), find relevant content (search_docs), and read specific content (get_doc). No create/update/delete is expected for a documentation corpus, so there are no meaningful gaps.
Read one full Atisbo documentation page as markdown, by its site-relative URL (for example /docs/api/webhooks).
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Site-relative URL of the page, as returned by search_docs or list_docs. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already establish the read-only, non-destructive nature, so the description doesn't need to repeat that. It adds useful behavioral detail by stating the whole page is returned as Markdown and that the input is a site-relative URL, which clarifies exactly what the tool does beyond a simple read hint.
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 description is one compact, front-loaded sentence that includes the key action, resource, return format, and an example. No filler words; every element contributes to correct invocation.
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 one-parameter read-only tool with a clear output format and sibling tools referenced by the schema, the description is fully sufficient. No output schema is needed because the description states the return format as Markdown, and the annotations already signal safety.
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. The description adds value beyond the schema by providing a concrete example URL ('/docs/api/webhooks') and restating the site-relative-URL requirement in context, helping an agent correctly format the single parameter.
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 ('Read') and resource ('Atisbo documentation page'), and uniquely identifies the addressing scheme (site-relative URL) and return format (markdown). This clearly differentiates it from sibling tools list_docs and search_docs, which return collections or search 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?
The description implies the intended flow: use search_docs or list_docs to obtain a site-relative URL, then call get_doc with that URL. The schema reinforces this by stating the URL is 'as returned by search_docs or list_docs.' It does not explicitly list exclusions, but the usage context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List Atisbo documentation pages with their URL, title and description. Omit limit for the whole corpus; pass limit to cap the response.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of pages to return (1-50). Omitted, non-integer, or out-of-range values return the WHOLE corpus — this tool never pages, it only trims. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint and destructiveHint annotations, the description discloses non-obvious behavior: omitting limit returns the whole corpus and passing limit only trims, not pages. It also specifies the returned attributes, which is useful behavioral context for a read-only listing tool.
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 with no filler: the first states the action and result fields, the second explains the optional parameter behavior. The most important usage note 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 simple list tool with one optional parameter, read-only annotations, and no output schema, the description fully covers what is returned and how the only parameter behaves. There is no missing information an agent needs to call 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?
The input schema already documents the limit parameter thoroughly, including that omitted, non-integer, or out-of-range values return the whole corpus and that the tool never pages. The description reinforces the omit-versus-pass distinction but adds no new parameter meaning beyond the schema, 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 uses a specific verb and resource ('List Atisbo documentation pages') and states the output fields (URL, title, description). It is clearly distinct from the get_doc and search_docs siblings by nature of the operation, though it does not explicitly name those alternatives.
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 only usage guidance concerns the limit parameter: omit it for the whole corpus or pass it to cap the response. There is no guidance on when to use list_docs versus get_doc or search_docs, leaving tool-selection context implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Atisbo documentation by keyword or natural-language question. Returns ranked page titles, URLs, descriptions and match scores.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum hits to return (default 5). | |
| query | Yes | Keywords or a natural-language question. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds that results are 'ranked' and include 'match scores', conveying ordering and scoring behavior. It does not disclose deeper behavioral details such as ranking algorithm or pagination, but the annotation coverage lowers the burden, making 3 appropriate.
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 description is two short declarative sentences with no wasted words. The verb and resource are front-loaded, followed by a concise specification of the return format. Every clause adds value.
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 read-only search tool with two flat parameters and no output schema, this description is complete. It explains what to send (query, with limit in schema) and what to expect back (ranked page titles, URLs, descriptions, match scores), satisfying the return-format burden imposed by the missing output schema. Nothing needed for correct invocation 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%, with both query and limit already described in the input schema. The tool description essentially restates the query parameter's purpose and adds no new meaning about limit defaults, query formatting, or edge cases. Baseline 3 is correct when the schema already documents the parameters.
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 verb ('Search'), a resource ('Atisbo documentation'), the accepted input style ('keyword or natural-language question'), and the return fields ('ranked page titles, URLs, descriptions and match scores'). This clearly differentiates from the sibling tools get_doc and list_docs by action and output shape, even without naming 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?
The description implies the tool is used for query-based lookup by describing the supported input forms, but it does not explicitly state when to prefer search_docs over get_doc or list_docs, nor any exclusions or alternative conditions. Guidance is present but relies on inference from the verb 'search' and the tool's name.
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.
get_doclist_docssearch_docsSearch and fetch AgendaForge public documentation and marketing content. No authentication needed.
Search and read the public Applivery docs (MDM & app distribution). Read-only, no auth.
Search and read Empryo's documentation. Read-only, no auth, no local access.
Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.
