Read-only MCP access to stepcode.dev's how-to corpus: analysis pages by tool.
Scored across 4 tools
Three tools are clearly distinct: get_howto_page retrieves a single page, list_analysis_families provides aggregated family metadata, and search_howto_pages filters the index. However, search_howto_pages with no arguments explicitly behaves identically to list_howto_pages, creating a mild overlap that could cause an agent to pick either one for the same task.
All tool names follow a consistent verb_noun pattern with clear actions: get, list, search. The naming is uniform, predictable, and easy to extend.
Four tools is well-scoped for a read-only documentation/how-to server: one for detail retrieval, one for aggregated families, one for full listing, and one for filtered search. Each tool earns its place without redundancy or bloat.
The surface covers the full discovery-and-retrieval lifecycle: browse families, list all pages, search/filter the index, and fetch detailed page content. There are no obvious dead ends or missing operations for the stated purpose.
Get the full howto/v2 contract for one page by slug (from list_howto_pages / search_howto_pages): intro, per-step teach/intent/code, divergence notes, cross-tool links, and grounding.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | How-to page slug, e.g. flight-risk-predict-which-employees-will-resign-in-excel. |
| Name | Required | Description |
|---|---|---|
| page | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is covered. The description adds useful context about what the 'full contract' includes (intro, per-step content, divergence notes, cross-tool links, grounding), but does not go beyond that to disclose rate limits, error behavior, or other operational traits.
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?
One compact sentence front-loads the primary action and resource, then efficiently enumerates the returned content. There is no filler or repetition of schema details.
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 only one required parameter, a fully documented schema, an output schema, and read-only annotations, the description covers the essential workflow: obtain a slug from list/search, then fetch the full page. Nothing critical 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 the slug parameter already includes a concrete example. The description reinforces that the slug identifies one page and originates from sibling tools, but adds little 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?
The description uses a specific verb ('Get') and resource ('the full howto/v2 contract for one page by slug'), and clearly distinguishes this single-page retrieval tool from the sibling list/search tools by naming them as sources of the slug. An agent can tell exactly what this tool does and what it returns.
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 explicitly says the slug comes from list_howto_pages / search_howto_pages, which tells the agent when to use this tool: after finding a page via the sibling tools. It does not state explicit when-not conditions for sibling alternatives, but the context is clear enough for this simple one-parameter tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the analysis families on stepcode.dev (e.g. flight-risk, diversity-index-EBIT-impact) with the tools each is shown in and how many pages exist for it.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| families | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the operation as read-only and non-destructive. The description adds useful behavioral detail by specifying what the listing includes (tools shown and page counts), which goes beyond the structured annotations.
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 well-structured sentence that front-loads the action and resource, includes clarifying examples, and summarizes the output. Every element earns its place with no 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?
For a simple zero-parameter list operation with a read-only annotation and an output schema present, the description provides enough context. It covers what is listed, where it is from, and what is included in the result.
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 has zero parameters, so parameter semantics are not a burden on the description. The schema fully covers this case, and the description contributes relevant detail about what the result set represents.
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 ('List') and resource ('analysis families on stepcode.dev'), provides concrete examples, and clarifies the output includes associated tools and page counts. This clearly distinguishes it from sibling tools that operate on howto pages.
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 tool's scope obvious but does not explicitly say when to choose it over alternatives or mention exclusions. Usage is implied through the resource type and examples, but no direct comparison to sibling tools is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List every published how-to page on stepcode.dev — 36 analysis x tool cells (Excel, Google Sheets, R, Python, SQL, DAX/Power BI) with slug, title, analysis family, tool, vertical and whether the tool's approach diverges from the others.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| pages | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish this is a safe read-only operation. The description adds useful behavioral scope: only published pages, all 36 analysis x tool cells, and the divergence flag. It does not mention ordering or pagination, but the fixed small set and zero parameters make those less critical.
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 dense sentence leads with the verb and resource, then packs the scope and returned fields into a well-organized em-dash clause. There is 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 no parameters, an output schema available, and annotations covering the safety profile, the description provides the remaining essential context: exactly what the listing contains and its scope. Nothing critical is missing for an agent to invoke 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?
The input schema has zero parameters and 100% schema description coverage, so there is no parameter burden for the description to carry. No parameter documentation is needed.
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 object: 'List every published how-to page on stepcode.dev.' It then enumerates the exact fields returned, making it clearly distinct from get_howto_page (single page) and search_howto_pages (filtered lookup).
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 clearly implies this is for full enumeration of all how-to pages, but it does not explicitly state when to choose this tool over search_howto_pages or get_howto_page. No alternatives or exclusion conditions are named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Filter the how-to index by analysis family, tool, vertical, and/or a case-insensitive text query against title, analysis name, intro, problem statement, and step operations (with practitioner-synonym coverage, e.g. attrition/turnover/churn, logistic regression/classifier, power bi/dax, diversity/simpson/blau). All filters are optional and combine with AND; call with no arguments to get every page (same as list_howto_pages).
| Name | Required | Description | Default |
|---|---|---|---|
| tool | No | Tool slug, e.g. excel, sheets, r, python, sql, dax. | |
| query | No | Case-insensitive text query against title, analysis name, intro, problem statement, and step operations. | |
| vertical | No | Vertical slug, e.g. hr. | |
| analysisSlug | No | Analysis family slug, e.g. flight-risk-predict-which-employees-will-resign. |
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| pages | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as read-only and non-destructive, and the description adds meaningful behavior: all filters are optional and AND-combined, the query is case-insensitive, and it includes practitioner-synonym expansion with concrete examples. There is no conflict with annotations.
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 dense sentences deliver all essential information with no filler. The primary filtering action and dimensions are front-loaded, and the synonym examples and no-argument equivalence are compact and useful.
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 search tool with four optional parameters, an output schema, and sibling comparison, the description covers filters, combination logic, synonym behavior, and the empty-argument case. No critical operational detail seems 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 coverage is 100%, so the parameters are already documented individually. The description adds cross-parameter semantics that the schema does not, namely AND combination, optionality, case-insensitive matching, synonym coverage, and the effect of no arguments.
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 precise action—filter the how-to index—and lists the filtering dimensions: analysis family, tool, vertical, and text query. It distinguishes itself from list_howto_pages by noting that a no-argument call returns every page, and from get_howto_page by targeting the index rather than 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 explains when the tool is appropriate: filtering by optional criteria, with AND combination, and explicitly notes the no-argument case is equivalent to list_howto_pages. It stops short of explicitly instructing when to choose get_howto_page over this tool, though the sibling names make that distinction inferable.
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.
search_howto_pages1 field changedInput schema / properties / query / descriptionPrevious value: -"Case-insensitive substring match against title + analysis name."New value: +"Case-insensitive text query against title, analysis name, intro, problem statement, and step operations."get_membership_offerget_membership_offerget_howto_pagelist_analysis_familieslist_howto_pagessearch_howto_pagesRead-only MCP access to devplane.dev's public pages, FAQ corpus and comparisons.
Public read-only MCP for products, frameworks, guides, methodology, and blog metadata.
Read-only MCP for the Eco game wiki: search, Markdown pages, and wiki_* lookups. No keys, no writes.
Read-only MCP over the LivingMeta AI-in-Research corpus: 12,400 papers, gaps, priority agenda.
Add one secure layer between your agents and this server.
