Toofi Dental Planning MCP

Generate dental treatment-plan PDF

generate_dental_treatment_plan_pdf

Idempotent

Start the real Toofi headless treatment-plan pipeline from structured clinical findings: create a service-user runtime plan, invoke AI plan generation, and return an operation id for polling toward a patient-facing PDF output.

Input Schema

TableJSON Schema

Name	Required	Description
`patient`	No
`agent_id`	No	Calling agent identifier.
`agent_key`	No	Toofi agent API key. May also be supplied as X-Toofi-Agent-Key header.
`ai_preset`	No
`clinic_id`	No	Clinic identifier for mandate-scoped production execution.
`intent_id`	No	Root agent intent id.
`mandate_id`	No	Clinic or agent mandate id. Optional in public demo mode.
`request_id`	No	Idempotency and correlation id echoed in Toofi responses.
`presentation`	No
`principal_id`	No	Human or clinic principal on whose behalf the agent acts.
`session_token`	No	Alias for runtime_session_token.
`clinical_input`	Yes
`toofi_agent_key`	No	Alias for agent_key.
`runtime_session_token`	No	Toofi runtime actor token for service-user scoped execution. May also be supplied as x-toofi-session-token header.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ok`	No
`mode`	No
`status`	No
`endpoint`	No
`timestamp`	No

TDQS

A4.1/5.0

Behavior4/5

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

Annotations cover safety profile (readOnly=false, destructive=false, idempotent=true). The description adds valuable context about the async nature (operation ID for polling) and the pipeline steps, going beyond the annotations without contradicting them.

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

Conciseness4/5

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

The description is a single sentence but efficiently packs purpose, process, and output. It is front-loaded with the key verb and resource, and every phrase is useful. Slightly dense but not wasteful.

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?

Given the tool's complexity (14 parameters, nested objects), the description gives a solid overview of the workflow and return type, relying on the output schema for return details. It could mention authentication prerequisites, but those are already in the schema.

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

Parameters3/5

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

Schema description coverage is 71%, so the schema already documents most parameters. The description adds no parameter-specific meaning and does not compensate for the undocumented parameters, so a baseline of 3 is appropriate.

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 clearly states the tool starts the Toofi headless treatment-plan pipeline, creates a runtime plan, invokes AI generation, and returns an operation ID for polling. This distinguishes it from siblings like generate_treatment_plan_draft and get_dental_plan_operation_status.

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 provides clear context that this is the 'real' production pipeline for generating a patient-facing PDF, implying use for final outputs rather than drafts. However, it does not explicitly state when not to use it or name alternative tools, so it stops short of a 5.

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

All Toofi Dental Planning MCP tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.3/5.0

Disambiguation3/5

Several tools have overlapping purposes, particularly example_en, example_pl, example_ru, example_sk, example_ua, example_uk, and get_example_result, which all return example PDFs. Also, example_ua and example_uk are explicitly aliases for the same Ukrainian example, creating direct ambiguity. Core clinical tools are distinct, but the example/demo cluster muddies the boundary.

Naming Consistency4/5

Most tools follow a snake_case verb_noun pattern (e.g., list_patients, create_agent_checkout_session, generate_price_estimate), but a few deviations exist: example_en/pl/ru/sk/ua/uk lack a verb prefix, and get_example_result seems to duplicate example_en. The 'pano' abbreviation in start_pano_markup is also slightly inconsistent. Overall, the pattern is mostly predictable.

Tool Count2/5

With 32 tools, the count is too high for the apparent scope of dental planning. Many tools are redundant example/demo variants (e.g., 6 language-specific example tools plus get_example_result, and multiple demo getters/listers). This bloat suggests the tool set could be consolidated to a more focused 15-20 tools without losing core functionality.

Completeness3/5

The core workflow is covered: generating plans, retrieving patients/plans, pricing, and billing. However, there are notable gaps such as no update or delete operations for plans or patients, no create patient tool, and no way to modify pricing beyond import_price_csv. The demo tools partially compensate by offering sample data, but the production lifecycle is incomplete.

Resources

Need Help?