Fill standard legal agreement templates (NDAs, SAFEs, NVCA docs, employment) as DOCX files.
Scored across 4 tools
list_templates and search_templates are the closest pair, but the descriptions explicitly draw the boundary (browse catalog vs. BM25 keyword search) and even instruct when to use which. get_template vs. list_templates is clearly separated by detail level, and fill_template is unique. Minor residual overlap between listing and searching keeps this from a perfect score.
All four tools follow a strict verb_noun pattern: fill_template, get_template, list_templates, search_templates. Verb choice is predictable and the noun is uniform, making the set easy to reason about.
Four tools map cleanly onto discovery (list/search), inspection (get), and output (fill) for a template server, with no redundancy. It is on the lean side — no field validation or document retrieval tool — but each tool earns its place.
The discovery-to-fill lifecycle is fully covered, including redline generation for field-selector templates. Gaps are minor: there is no way to fetch or manage previously generated documents or validate field values before filling.
Fill a legal agreement template with field values and return a document via URL or MCP resource preview metadata. For field-selector templates (e.g. NVCA), also generates a redline (track-changes) document comparing the filled output against the standard form.
| Name | Required | Description | Default |
|---|---|---|---|
| values | No | Field values to fill in the template. | |
| template | Yes | Template ID, e.g. "common-paper-mutual-nda". | |
| return_mode | No | Artifact return mode. Defaults to "url". | |
| redline_base | No | Base document for redline comparison. "source" = raw standard form (default), "clean" = cleaned intermediate. | |
| include_redline | No | Generate a redline (track-changes) document. Defaults to true for field-selectors. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool returns a document via URL or MCP resource, and that redline generation occurs for field-selector templates. With annotations only indicating it is not read-only and not destructive, the description adds meaningful behavioral context beyond the 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?
The description is two sentences, front-loaded with the primary action, and the second sentence adds an important conditional behavior. No redundant information.
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?
The description explains the tool's purpose, return modes, and the special redline case. Given the tool has no output schema and a nested `values` object, the description is sufficiently complete for the agent to understand the tool's behavior, though it could elaborate on expected `values` structure, but the schema covers that.
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 covers all 5 parameters with descriptions (100% coverage). The description adds contextual information about redline generation for field-selector templates but does not add per-parameter details beyond the schema, so the baseline of 3 is appropriate.
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 states the tool fills a legal agreement template with field values and returns a document, distinguishing it from sibling tools that only list or retrieve templates. It also specifies the redline generation behavior for field-selector 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?
While it doesn't name alternative tools, the description clearly implies the tool is for creating filled documents, and the sibling names suggest alternatives for reading templates. The conditional redline behavior for field-selector templates provides clear context on when that feature applies.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch a single template definition with full field metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| template_id | Yes | Template ID, e.g. "common-paper-mutual-nda". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds return-value context ('full field metadata') but does not discuss potential errors or edge cases. Given the simple read operation, the additional context is minimal but acceptable.
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 concise sentence that front-loads the purpose and contains no extraneous information.
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 read-only tool with one parameter and no output schema, the description sufficiently conveys the purpose and hints at the return content ('full field metadata'). It is adequate but could be more explicit about the return structure or non-existence handling.
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%, with a clear description and example for template_id. The tool description adds no additional parameter semantics beyond the schema, 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?
The description clearly states the action ('Fetch'), the resource ('a single template definition'), and adds a distinguishing detail ('full field metadata'), differentiating it from list_templates and search_templates by the 'single' qualifier.
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 does not explicitly state when to use this tool over alternatives like list_templates or search_templates, nor does it mention prerequisites or exclusion criteria. The 'single' qualifier implicitly contrasts with list/search, but no direct guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all available legal agreement templates as a paginated compact catalog. Returns lightweight metadata for discovery — call get_template for full per-field detail. Templates are returned in stable lexicographic order by template_id. For finding templates by topic, jurisdiction, or source, use search_templates instead.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Page size (default 25, max 100). | |
| cursor | No | Opaque pagination cursor returned by a prior call. Omit on the first page. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark readOnlyHint=true and destructiveHint=false; description adds that results are paginated, compact/lightweight metadata, and in stable lexicographic order by template_id. It does not describe return fields, but that's acceptable given the 'call get_template' pointer.
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, first sentence immediately states purpose; no filler or redundancy. Every sentence adds distinct information (scope, guidance, ordering/alternative).
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 low-complexity read-only list tool with full schema coverage and a pointer to get_template for detail, the description covers usage and behavior adequately. The absence of an output schema is mitigated by the explicit statement that it returns lightweight metadata for discovery.
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 covers 100% of parameters with descriptions for limit and cursor, so the description adds little beyond mentioning pagination. Baseline 3 applies because schema does the heavy lifting.
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?
Description opens with 'List all available legal agreement templates as a paginated compact catalog' — a specific verb and resource. It distinguishes from siblings by noting get_template for full detail and search_templates for topic-based discovery.
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?
Explicitly says 'call get_template for full per-field detail' and 'use search_templates instead' for topic/jurisdiction/source searches. This clearly delineates when to use this tool versus alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for legal agreement templates by keyword. Uses BM25 ranking to find the most relevant templates matching your query. Searches across template names, descriptions, categories, sources, and field definitions. Use this instead of list_templates when you know what kind of agreement you need.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query. Examples: "NDA", "employment offer letter", "NVCA stock purchase", "data processing GDPR", "non-compete Wyoming". | |
| source | No | Optional source filter (exact, case-insensitive). Values: "Common Paper", "Bonterms", "Y Combinator", "NVCA", "OpenAgreements". | |
| category | No | Optional category filter (exact, case-insensitive). Values: confidentiality, employment, sales-licensing, data-compliance, deals-partnerships, professional-services, venture-financing, other. | |
| max_results | No | Maximum results to return (1-50, default 10). |
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 goes beyond annotations by revealing the BM25 ranking algorithm and specifying the exact searchable fields (names, descriptions, categories, sources, field definitions). This provides useful behavioral context beyond what structured data conveys, though it omits details like result count handling or ordering 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?
The description is three sentences long and front-loaded with the primary purpose in the first sentence. The second sentence adds valuable ranking details, and the third gives usage guidance. No filler or redundancy—every sentence earns its place.
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 search tool, the description is complete: it states what it searches, how it ranks results, and when to use it. There is no output schema, so return value explanation is not required, and the parameter scope is fully covered by the schema. The guidance about using it instead of list_templates completes the contextual picture.
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. However, the description adds meaning for the query parameter by stating it searches across names, descriptions, categories, sources, and field definitions, giving insight into how the query behaves. This is more than just restating the schema and adds value for parameter understanding.
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 states a specific verb ('Search') and resource ('legal agreement templates'), and further specifies that it searches by keyword. It is explicitly differentiated from the sibling tool list_templates by saying 'Use this instead of list_templates when you know what kind of agreement you need,' making it obvious what this tool does that others don't.
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 an explicit usage guideline: 'Use this instead of list_templates when you know what kind of agreement you need.' This is a clear when-to-use instruction with a named alternative, which is exactly what the dimension asks for. It also implies that list_templates is for browsing all templates, adding further context.
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.
fill_template1 field changedInput schema / properties / include_redline / descriptionPrevious value: -"Generate a redline (track-changes) document. Defaults to true for recipes."New value: +"Generate a redline (track-changes) document. Defaults to true for field-selectors."check_signature_statussend_for_signaturelist_templates4 fields changedInput schema / additionalPropertiesAdded value: +falseInput schema / properties / cursorAdded value: +{
+ "description": "Opaque pagination cursor returned by a prior call. Omit on the first page.",
+ "type": "string"
+}Input schema / properties / limitAdded value: +{
+ "description": "Page size (default 25, max 100).",
+ "maximum": 100,
+ "minimum": 1,
+ "type": "integer"
+}Input schema / properties / modeRemoved value: -{
- "description": "Response detail mode. Defaults to \"compact\".",
- "enum": [
- "compact",
- "full"
- ],
- "type": "string"
-}list_templates1 field changedInput schema / properties / mode / descriptionPrevious value: -"Response detail mode. Defaults to \"full\"."New value: +"Response detail mode. Defaults to \"compact\"."send_for_signature1 field changedInput schema / properties / document_nameAdded value: +{
+ "description": "Filename for the document (e.g. 'Bonterms Mutual NDA.docx'). Auto-detected from download URL if not provided.",
+ "type": "string"
+}check_signature_status2 fields changedInput schema / properties / api_keyRemoved value: -{
- "description": "Required to download the signed document when completed.",
- "type": "string"
-}Input schema / properties / envelope_id / descriptionAdded value: +"The envelope ID returned by send_for_signature."connect_signing_providerdisconnect_signing_providersend_for_signature5 fields changedInput schema / properties / api_keyRemoved value: -{
- "description": "Your open_agreements_api_key.",
- "type": "string"
-}Input schema / properties / download_url / descriptionPrevious value: -"URL to download the DOCX (for remote MCP). Use the download_url from fill_template."New value: +"URL to download the DOCX file. Use the download_url from fill_template."Input schema / properties / file_pathRemoved value: -{
- "description": "Local path to the DOCX file (for stdio MCP server).",
- "type": "string"
-}Input schema / properties / signers / descriptionPrevious value: -"Signers and CC recipients."New value: +"Signers and CC recipients. First signer maps to party_1, second to party_2."Input schema / requiredPrevious value: -[
- "signers",
- "api_key"
-]New value: +[
+ "signers"
+]search_templatessend_for_signature3 fields changedInput schema / properties / download_urlAdded value: +{
+ "description": "URL to download the DOCX (for remote MCP). Use the download_url from fill_template.",
+ "type": "string"
+}Input schema / properties / file_path / descriptionPrevious value: -"Path to the DOCX file to send for signature."New value: +"Local path to the DOCX file (for stdio MCP server)."Input schema / requiredPrevious value: -[
- "file_path",
- "signers",
- "api_key"
-]New value: +[
+ "signers",
+ "api_key"
+]connect_signing_provider3 fields changedInput schema / properties / api_keyAdded value: +{
+ "description": "Your open_agreements_api_key.",
+ "type": "string"
+}Input schema / properties / redirect_uriRemoved value: -{
- "description": "OAuth redirect URI.",
- "type": "string"
-}Input schema / requiredAdded value: +[
+ "api_key"
+]check_signature_statusconnect_signing_providerdisconnect_signing_providersend_for_signaturefill_templateget_templatelist_templatesFill in 1,000+ legal PDF templates in many languages, get a signed PDF back. Free, no API key.
Generate attorney-drafted NDAs, MSAs, DPAs, and more as PDF, ODT, or Markdown. No account required.
Reusable docx templates: placeholders for proposals, contracts, quotes, SOWs.
E-signatures for contracts and NDAs. Draft with AI, review, and send for signature.
Add one secure layer between your agents and this server.
