Superset's published program templates and page metadata, and a way to request a trial.
Scored across 3 tools
The three tools target distinct actions: fetching a marketing page, listing training templates, and requesting a coach trial. There is minor potential overlap between get_page and list_program_templates if a template is also a marketing page, but descriptions clarify their intended use.
All tools follow a consistent snake_case verb_noun pattern: get_page, list_program_templates, request_coach_trial. The convention is predictable and easy to parse.
Three tools are well-scoped for a narrow public catalog and trial-request surface. Each tool has a clear purpose and no extraneous operations.
The tool set covers template listing and single-page retrieval, but lacks a way to list or search marketing pages, forcing agents to know exact paths. This is a notable discovery gap for a catalog server, though basic operations are present.
Get the title, description, and URL of a Superset marketing page by its path, e.g. "/platform" or "/training".
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Page path starting with '/', e.g. '/platform' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully discloses the return fields (title, description, URL), which matters because there is no output schema, but it says nothing about failure behavior for an unknown or malformed path.
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 sentence, front-loaded with the verb and resource, with the return fields and the path format packed in without waste. Nothing could be removed without losing meaning.
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 with full schema coverage and readOnly/openWorld annotations, the description covers purpose, input format, and the returned fields (compensating for the absent output schema). Only the behavior on an invalid or missing path is left unstated.
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 single parameter already documents the leading-slash format and gives '/platform' as an example. The description adds a second example ('/training') and confirms these are marketing-site paths, but that is marginal enrichment over structured data already provided.
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 ('Get') and resource ('a Superset marketing page') and enumerates exactly what is returned (title, description, URL). The sibling tools (list_program_templates, request_coach_trial) are unrelated, so an agent can route to this one without ambiguity.
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 by 'by its path' plus two example paths; there is no explicit statement of when to use this versus anything else, and no mention of prerequisites. Since the siblings are in a different domain, the omission is low-risk, but the guidance 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.
List Superset's published training program templates. Returns each template's slug, name, description, and public URL.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description earns credit by disclosing the shape of the result (slug, name, description, public URL), which matters because there is no output schema. It does not mention ordering, pagination, or count, which for a zero-parameter list tool is a minor gap.
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 the verb and resource, second sentence delivering the return-shape detail. Every phrase carries information and nothing is repeated from the title.
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 zero-parameter read tool with no output schema, the description covers both what is listed and what each item contains, which is the essential information. It could optionally state result ordering or whether the list is exhaustive, but an agent has enough 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?
The tool takes no parameters and the schema has additionalProperties=false, so there is nothing for the description to disambiguate. Baseline of 4 applies for a zero-parameter tool.
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 ('List') and a precisely scoped resource ('Superset's published training program templates'), and even enumerates the returned fields. The scope word 'published' distinguishes it from any hypothetical unpublished-template tool, and no sibling (get_page, request_coach_trial) overlaps with this capability.
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: an agent can infer it should call this when it needs the catalog of training templates. There is no explicit 'use when' clause, no exclusion, and no mention of the siblings, though the siblings are unrelated enough that little guidance is needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Request a free Superset coach trial for the person you work for. The Superset team gets their name and email and follows up with them. Ask for their consent first.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | The person's email | ||
| last_name | No | The person's last name | |
| agent_name | No | Your product's name, e.g. 'Claude', shown to us for attribution | |
| first_name | Yes | The person's first name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare non-read-only, non-destructive, non-idempotent behavior, and the description adds genuinely new context: a third party (the Superset team) receives the person's name and email and will follow up with them, which an agent cannot infer from the schema. It does not address duplicate requests or what a repeat call does, though idempotentHint=false flags that.
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, front-loaded with the action, then the downstream effect, then the consent prerequisite. Nothing is redundant.
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 submission tool with full schema coverage and annotations, the description covers the essentials: who is affected, who receives the data, what happens next, and the consent precondition. Return-value behavior is the only unaddressed area, and no output schema exists.
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 each field is already documented, including agent_name's attribution purpose. The description only echoes 'name and email'; baseline 3 applies since the schema carries the parameter 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 action (request a free Superset coach trial) and scopes it precisely: it is performed on behalf of the person the agent works for, not the agent itself. That framing makes it unmistakable against unrelated siblings like get_page and list_program_templates.
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?
Provides a clear prerequisite — obtain the person's consent before calling — and clarifies the acting-on-behalf context. It stops short of stating when-not to use it or naming any alternative path, but none of the listed siblings overlaps with 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.
get_pagelist_program_templatesrequest_coach_trialRead-only senior-care exit routes, duplicate-referral deadlines, and templates; no PII or sending.
Public read-only MCP for products, frameworks, guides, methodology, and blog metadata.
Read-only access to Kanbai's public project templates and SOPs. Public, no authentication.
Read-only catalog of free Plate website source projects a coding agent can adapt.
Add one secure layer between your agents and this server.
