Practical answers for small business owners from the Small Business Owners Community & Businessing.
Scored across 3 tools
Each tool has a clearly distinct role: search_library finds content by query, whats_new lists recent content, and get_document retrieves details for a specific result. Although search_library and whats_new both return lists, their query-driven versus recency-driven purposes are explicitly separated.
get_document and search_library follow a clear verb_noun snake_case pattern, while whats_new is a noun phrase rather than a verb_noun construction. The deviation is minor and still readable and predictable.
The three tools cleanly cover the core workflows: searching by question, browsing newest additions, and opening a specific result. Each tool earns its place with no redundancy or unnecessary surface area.
The set covers discovery via search and recency plus detail retrieval, with an intentional external link for full content. A minor gap is the lack of category/topic browsing or listing all episodes beyond the newest set, but agents can work around this using search.
Get the opening and outline of one post or episode, with the link to the full thing. Use after search_library or whats_new when the person wants more on one result. Never returns the full post.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The id shown on a search_library or whats_new result, for example "referral-partnership-ideas-without-selling." |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds the crucial behavioral limit 'Never returns the full post,' which stops an agent from expecting or looping for full content, and notes the outbound link. It does not mention rate limits or pagination, so it is not exhaustive.
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 with the capability first, the routing rule second, and the key limitation last. Nothing is redundant and every sentence carries information an agent needs.
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?
A single-parameter read tool with full annotation coverage and no output schema; the description nonetheless characterizes the return (opening, outline, link) and its truncation limit. Nothing required to call it correctly 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?
Only one parameter and schema description coverage is 100%; the schema already explains that the id comes from a search_library or whats_new result and gives an example value. The description adds no syntax or format detail beyond that, 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 (get) and resource (the opening and outline of one post or episode) plus what comes back (a link to the full thing). The scope restriction 'one post or episode' makes it clearly distinct from the list-oriented siblings search_library and whats_new.
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 an explicit chaining rule: 'Use after search_library or whats_new when the person wants more on one result.' That names the alternatives and the condition that selects this tool, so an agent knows exactly where it sits in a workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the library for what the Small Business Owners Community has learned about an owner's question. Use this first for any small business question, however it's worded: "raise my prices," "a client won't pay," "can't find good people," "working too many hours," "nobody to talk to about the business." Returns up to 8 short passages, each with a match label (strong, related or weak), the title, date, read link, a watch link when there is one, and an id to pass to get_document.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many passages to return, 1 to 8. Default 5. | |
| query | Yes | The owner's question or topic in plain words, for example "raise my prices without losing clients." |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. Beyond that, the description discloses the result contract: up to 8 short passages, each with a match label (strong/related/weak), title, date, read link, optional watch link, and an id for get_document — valuable detail given 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 core instruction is front-loaded in the first sentence, and the example phrasings are compact illustrations rather than filler. It is dense with useful content, though the long inline list of example questions and return fields makes it a somewhat heavy single block.
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 two-parameter read-only search with no output schema, the description supplies everything an agent needs: when to reach for it, how to phrase the query, how many results come back, and what fields each result carries including the id for follow-up. Nothing material 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 coverage is 100%, so the baseline is 3, and the description earns a bump by clarifying intent: the query should be plain-words phrasing of the owner's question ('however it's worded') and the result volume is capped at 8 short passages. It does not restate the limit's default of 5 or its 1-8 bounds, which the schema already handles.
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 and resource ('Search the library') plus the domain it searches ('what the Small Business Owners Community has learned') and the expected return shape. It implicitly separates itself from siblings by saying the returned id is 'to pass to get_document', so an agent can tell it apart from get_document and whats_new without opening either 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?
It gives an explicit priority instruction ('Use this first for any small business question') and backs it with paraphrased example phrasings ('raise my prices', 'a client won't pay', 'nobody to talk to about the business') that show the breadth of acceptable queries. The handoff to get_document covers the natural next step, leaving little to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the newest posts and episodes added to the library, newest first. Use when someone asks what's new, what Pat talked about lately, or what was on the latest Businessing episode. Returns 8 unless count is set.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | How many to return, 1 to 15. Default 8. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds useful behavior beyond that: results are ordered newest first and the default return size is 8. It does not describe pagination or what fields each item contains, but for a simple read that is minor.
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 core action and ordering, then usage triggers, then the return-size caveat. 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?
For a single-optional-parameter read tool with rich annotations and no output schema, the description covers purpose, ordering, usage triggers, and default result size. Nothing an agent needs to invoke it correctly 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 coverage is 100% and the count parameter already documents range 1-15 and default 8. The description's 'Returns 8 unless count is set' restates the schema default rather than adding new meaning, 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 and resource ('List the newest posts and episodes added to the library') plus ordering ('newest first'), which clearly separates it from search_library and get_document. It stops short of naming those siblings explicitly, so it is clear but not maximally differentiated.
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 concrete when-to-use triggers ('what's new', 'what Pat talked about lately', 'latest Businessing episode'), which is strong positive guidance. It does not state when to prefer search_library instead, so the routing is implied rather than complete.
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_documentsearch_librarywhats_newBusiness insurance advice and real carrier quotes for U.S. small businesses from a licensed broker.
Read-only small business Q&A, product prices, IRS datasets and calculators from ProfitDrawer.
Bookkeeping for owner-operated businesses. Query transactions, invoices, and reports.
Invoices, payments, expenses, customers, deals, proposals, eSign and reports for small businesses.
Add one secure layer between your agents and this server.