Bucky

Create or attach to a project

saveToProject

Idempotent

Create a project (create), attach lots (attach_parcels), or attach a knowledge reference (attach_reference). Pass projectId or project; with neither, the result lists projects and writes nothing. For attach_parcels, copy lot.parcelExternalId from getFeasibilitySnapshot. preview=true returns the diff and writes nothing. A write returns a receipt. Not reversible on this surface.

Input Schema

TableJSON Schema

Name	Required	Description
`lat`	No	Latitude from getFeasibilitySnapshot. Supplied coordinates are never re-geocoded.
`lng`	No	Longitude from getFeasibilitySnapshot.
`name`	No
`role`	No	build is the lot being developed; context is surrounding land. Default build.
`action`	Yes	create: new project from a site. attach_parcels: attach lots to an existing project (use lot.parcelExternalId from getFeasibilitySnapshot). attach_reference: link a knowledge section to an existing project.
`address`	No	Street address of the site. On `create` this is geocoded server-side when lat/lng are not supplied, and is what gets recorded as the project address.
`context`	Yes	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`preview`	Yes	When true, return the field-level diff and write nothing.
`project`	No	Project name to match instead of a UUID, for attach_parcels and attach_reference. Matching more than one lists the candidates instead of guessing. Ignored by create.
`radiusM`	No	Search half-width in metres when resolving parcel ids. Default 150.
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`projectId`	No	Existing project UUID. Required by attach_parcels and attach_reference unless you pass `project`; ignored by create.
`externalRef`	No	Provenance of an imported project. Canonical form is `<system>:<id>` (e.g. `notion:<page-id>`). Unique per creator when set. Returned on getProjectContext. Distinct from idempotencyKey.
`sectionUuid`	No
`idempotencyKey`	No
`conversation_id`	No	Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.
`parcelExternalIds`	No	Source parcel ids to attach. Copy lot.parcelExternalId from getFeasibilitySnapshot. If they are not in the current area, pass a larger radiusM on attach_parcels.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 26, 2026

changedInput schema / properties / context / description

Previous value: -"Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""New value: +"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""

addedInput schema / properties / conversation_id

Added value: +{
+  "description": "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it.",
+  "type": "string"
+}

addedInput schema / properties / llm_model

Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}

changedInput schema / properties / parcelExternalIds / description

Previous value: -"Source parcel ids to attach. Copy lot.parcelExternalId from getFeasibilitySnapshot, or from bucky parcels search."New value: +"Source parcel ids to attach. Copy lot.parcelExternalId from getFeasibilitySnapshot. If they are not in the current area, pass a larger radiusM on attach_parcels."

changedInput schema / required

Previous value: -[
-  "action",
-  "preview",
-  "context"
-]New value: +[
+  "action",
+  "preview",
+  "context",
+  "llm_model"
+]

Changed2 schema fields changedSep 21, 2026

addedInput schema / properties / project

Added value: +{
+  "description": "Project name to match instead of a UUID, for attach_parcels and attach_reference. Matching more than one lists the candidates instead of guessing. Ignored by create.",
+  "maxLength": 200,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / projectId / description

Added value: +"Existing project UUID. Required by attach_parcels and attach_reference unless you pass `project`; ignored by create."

Changed4 schema fields changedSep 15, 2026

addedInput schema / properties / address / description

Added value: +"Street address of the site. On `create` this is geocoded server-side when lat/lng are not supplied, and is what gets recorded as the project address."

addedInput schema / properties / externalRef

Added value: +{
+  "description": "Provenance of an imported project. Canonical form is `<system>:<id>` (e.g. `notion:<page-id>`). Unique per creator when set. Returned on getProjectContext. Distinct from idempotencyKey.",
+  "maxLength": 200,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / lat / description

Added value: +"Latitude from getFeasibilitySnapshot. Supplied coordinates are never re-geocoded."

addedInput schema / properties / lng / description

Added value: +"Longitude from getFeasibilitySnapshot."

First observedSep 1, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description discloses that listing mode writes nothing, preview=true writes nothing, writes return a receipt, and operations are not reversible on this surface. This goes well beyond readOnlyHint/idempotentHint/destructiveHint and gives agents important side-effect knowledge.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five dense sentences with no fluff: the action list is front-loaded, then critical conditions (projectId/project, preview, receipt, reversibility) follow. Every sentence carries decision-relevant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 17-parameter tool with no output schema, the description covers the highest-risk behaviors: write suppression, project resolution, non-reversibility, and source of parcel IDs. It does not discuss sequencing constraints like conversation_id or idempotencyKey, but those are well documented in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is high (82%), and the description adds cross-parameter meaning not in the schema: how projectId/project relate to actions, the source of parcelExternalIds, and the preview write-suppression behavior. This exceeds the baseline expected with such coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names three concrete operations (create, attach_parcels, attach_reference) and a fallback listing behavior, each tied to a specific action value. This clearly differentiates the tool's multi-purpose behavior from siblings like updateProject and getProjectContext.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives actionable routing rules: pass projectId or project for attach actions, and with neither it lists projects and writes nothing. It also tells agents to copy lot.parcelExternalId from getFeasibilitySnapshot and explains preview behavior. It does not explicitly name when to prefer a sibling tool, but the action-level guidance is strong.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Bucky tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Create or attach to a project

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources