search_knowledge_baseAnswers from the app's own built-in knowledge base — 278 real support answers, extracted from the product. Measure Tech PRO is a full CRM for contractors; use this for how-do-I and does-it-do questions about measuring, drawings, the CRM, billing, and troubleshooting.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What the person wants to know, in their words |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the tool's safety profile is known. The description adds value beyond this by disclosing that results come from a fixed set of 278 extracted support answers, and that the tool is not a general web search. This gives the agent useful context about the tool's behavior and limitations.
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 sentences with no filler. The first sentence front-loads the primary behavior and source; the second adds relevant domain context and explicit usage guidance. Every sentence contributes to selection and 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 search tool with readOnlyHint=true and no output schema, the description is largely complete: it states the source, the domain, and the types of questions to use it for. It would be stronger if it explicitly addressed when to prefer sibling tools like search_forum, but that is not a major 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?
The input schema fully covers the single 'query' parameter with a min/max length and description. The tool description does not add additional parameter-level semantics, which is acceptable because schema coverage is 100%. 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 clearly identifies a specific verb and resource: searching the app's built-in knowledge base of real support answers. It further defines the scope with explicit topic areas (measuring, drawings, CRM, billing, troubleshooting). It is clear but does not explicitly name or contrast with sibling tools like search_forum.
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 gives explicit use cases: 'how-do-I and does-it-do questions' across specific domains. This tells an agent when the tool is appropriate. However, it does not provide exclusion criteria or point to alternatives such as search_forum for community-based questions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct actions, but get_product_overview, search_knowledge_base, and server_info all overlap on product-capability questions, and search_forum overlaps with get_roadmap for status discovery. The descriptions help direct usage, but ambiguity remains in a few pairs.
Nearly all tools follow a clean snake_case verb_noun pattern: get_pricing, heart_request, post_feature_request, search_forum. Minor deviations like server_info and my_requests are noun-phrase names, but they do not disrupt the overall readability.
Thirteen tools is well within the ideal range, and each tool earns its place. The set covers product info, pricing, forum engagement, knowledge base, waitlist, and contact without feeling padded.
The toolset covers the full customer-facing lifecycle: discover the product, check pricing, search and read forum threads, post requests, comment, heart, track personal requests, join the waitlist, and contact a human. There are no obvious dead ends for the stated purpose.