Find free math worksheets (Pre-Algebra–Calculus, Statistics) as printable PDFs with answer keys.
Scored across 2 tools
The two tools are cleanly separated: search_worksheets is a read-only discovery operation over topics, while create_worksheet is a generation action that consumes the topic ids search returns. There is no plausible scenario where an agent would confuse the two.
Both names follow the same verb_noun pattern (create_worksheet, search_worksheets) with consistent snake_case and matching domain nouns. The only variation is singular vs. plural noun, which is natural and non-distracting.
Two tools is thin even for a narrow worksheet-generation server; a discovery plus generation pair leaves little room for variation. It is defensible for the scope but sits at the borderline of under-provisioned.
The search-then-create lifecycle covers the core workflow end to end for an ephemeral PDF artifact, so CRUD gaps like update/delete are largely irrelevant here. Minor gaps remain: create_worksheet doesn't document how difficulty, question type, or problem count are selected, even though search_worksheets surfaces those attributes.
Makes a new printable math worksheet for one topic as a PDF, with a separate copy that includes the answer key. Every call gives a fresh version of the problems. Topics are identified by the topic ids that the topic search returns.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of problems, up to 40. Defaults to 20. | |
| topic | Yes | Topic id, as returned by the topic search, e.g. "factoring-trinomials". | |
| levels | No | Difficulty: any of easy, medium, hard. Defaults to the page default. | |
| version | No | Optional version number, to get the same sheet again. | |
| questionTypes | No | Optional question type ids for the topic, as returned by the topic search, to narrow the sheet. |
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 genuinely useful behavior beyond that: each call produces a fresh version of the problems (i.e., non-deterministic generation), and the output is a PDF plus a separate answer-key copy.
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 sentences, front-loaded with the core purpose, followed by the fresh-version behavior and the topic-id sourcing. Efficient with no filler, though the last sentence could be folded in more tightly.
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 output schema, the description does the work of explaining what comes back (PDF worksheet plus separate answer key). Combined with full schema parameter coverage and annotations covering safety, it is nearly complete; it omits delivery/location details of the generated file.
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%, so every parameter (count, topic, levels, version, questionTypes) is already documented in the schema. The description reinforces that topics come from topic search and hints at the version parameter, but adds little beyond the structured fields, so 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 (makes/creates), resource (printable math worksheet for one topic), and output format (PDF with a separate answer-key copy). This clearly distinguishes it from the sibling search_worksheets, which only finds existing sheets.
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?
Implies the usage path by directing the agent to obtain topic ids from 'the topic search,' but gives no explicit when-to-use/when-not statement or contrast with search_worksheets. Usage 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.
Finds Sigma Prep math worksheet topics (Pre-Algebra, Algebra 1, Geometry, Algebra 2, Precalculus, Calculus, Statistics) that match a request in plain words. Returns each topic's id, the difficulty levels it offers, its question types and its page on sigmaprep.io.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | What the worksheet is about, in plain words, e.g. "factoring trinomials" or "law of sines". | |
| course | No | Optional course name to narrow the search, e.g. "Algebra 2". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description goes beyond that by disclosing the shape of each hit (topic id, difficulty levels, question types, sigmaprep.io page), which is genuinely useful for planning follow-up calls. It stops short of noting result limits or ranking behavior.
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, no filler. The scope statement comes first and the return-shape sentence second, which is the right front-loading for a search tool.
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 output schema, the description carries the return-value burden and does so adequately by naming the per-result fields. It is still silent on result count, ranking, and pagination, which an agent may want when composing a query.
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 would be 3. The description nevertheless adds meaning the schema lacks: it enumerates the actual course values (Pre-Algebra through Statistics) that the free-text 'course' parameter accepts, effectively documenting the implied domain of a field the schema only illustrates with one example.
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 (Finds) and resource (Sigma Prep math worksheet topics) and enumerates the six course domains covered, so the agent knows exactly what universe is searchable. It is plainly distinguishable from the sibling create_worksheet, which is a write operation.
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 phrase 'match a request in plain words' implies how to query, and the sibling set makes the read-vs-write split obvious, but the description never states when to prefer this tool, when not to use it, or what happens if no topic matches. Usage is implied rather than specified.
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.
create_worksheet2 fields changedInput schema / properties / questionTypes / descriptionPrevious value: -"Optional question type ids from search_worksheets, to narrow the sheet."New value: +"Optional question type ids for the topic, as returned by the topic search, to narrow the sheet."Input schema / properties / topic / descriptionPrevious value: -"Topic id from search_worksheets, e.g. \"factoring-trinomials\"."New value: +"Topic id, as returned by the topic search, e.g. \"factoring-trinomials\"."create_worksheetsearch_worksheetsFree Pre-K to 5th grade math worksheets, worksheet makers, quizzes, teaching tools and curricula.
Free printable kids activities: word searches, mazes, color by number, sudoku and more.
The math tutor that asks why, for grades 1 to 6, with free printable word-problem worksheets.
Verified maths exercises for tutors and their students, each answer key right by construction.
Add one secure layer between your agents and this server.