Revit MCP

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

With no annotations provided, the description fully covers behavior. It discloses read-only status ('Read-only against APS'), idempotency, D1 table reads, error handling, and rate limits. The algorithm's fallback logic is also explained, providing complete transparency beyond structured fields.

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 well-structured with clear section headers and front-loaded usage guidance. Each section is purposeful, though the OSS upload size note under rate limits is tangential to this tool's operation. Slight over-inclusion prevents a perfect score.

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 tool has no output schema, and the description does not clearly explain what the agent will receive after execution. It mentions 'annotate with matching VDC rules' but never defines the result format, list of clashes, or pagination. Given the absence of an output schema, this is a significant gap for an agent to know how to use the returned data.

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%, with each parameter already thoroughly described (e.g., base64 URN pattern, case-insensitive match, typical categories). The description adds minimal additional parameter-specific meaning; it reinforces examples but does not materially extend beyond schema. Baseline 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 a specific action: 'Perform a lightweight clash analysis between two Revit categories' with a defined method (bounding-box overlap, fallback to shared-Level proximity). It is easily distinguished from sibling tools like revit_get_elements or revit_export_ifc, which address different operations.

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?

Explicit 'When to use' and 'When NOT to use' sections. It directly states not to substitute for Navisworks Manage for contractual reports, framing this as a 'first-pass coordination sniff test.' This gives the agent clear decision criteria and names an alternative.

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

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

With no annotations provided, the description fully discloses side effects (creates a Model Derivative job and IFC derivative), idempotency (safe to re-run, APS deduplicates), rate limits, scopes, and error handling. This goes far beyond basic safety hints and covers operational behavior comprehensively.

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?

Although lengthy, the description is well-structured with clear labels (When to use, When NOT to use, APS scopes, Rate limits, Errors, Side effects). Every sentence provides useful, non-redundant information, and the main use case is front-loaded.

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?

Given the complexity of the Model Derivative translation process and the absence of an output schema, the description covers prerequisites (translated URN), error scenarios, rate limits, side effects, and how to monitor progress (poll manifest). It is exceptionally complete for a tool with no annotations.

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 both parameters with descriptions and examples (100% coverage). The tool description adds value by explaining the default IFC version (IFC2x3 Coordination View 2.0) and the effect of include_properties on output, enhancing the schema's baseline.

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's purpose: to kick off a Model Derivative translation of a Revit URN into IFC for exchange with non-Autodesk tools. It uses specific verbs and resources, and explicitly distinguishes itself from revit_upload, which handles SVF/SVF2 viewing.

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?

Provides explicit when-to-use and when-not-to-use guidance, including not using it for web viewing (use revit_upload) and not calling repeatedly while a prior IFC job is in progress (poll the manifest instead). It also names the alternative for SVF/SVF2.

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

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

With no annotations provided, the description carries the full burden and delivers. It discloses read-only and idempotent side effects, a ~100 element limit, APS rate limits, detailed error codes with corrective actions, and the prerequisite of successful translation. This is far beyond what a schema reveals.

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 well-structured with labeled sections (When to use, When NOT to use, APS scopes, Rate limits, Errors, Side effects), making it easy to scan. It includes some extraneous details (e.g., OSS upload size limits) that are not directly relevant to this read-only fetch tool, but overall it is efficient for the complexity.

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 tool with no output schema and no annotations, the description is remarkably complete. It covers prerequisites, return field names, limits, error handling, and side effects. It even notes the approximate result count and model_id provenance. There are no major gaps for an agent to invoke and interpret results.

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%, with both parameters (model_id, category) already well-documented including patterns, examples, and case-insensitive matching. The description adds little beyond the schema for parameter meaning; it repeats the canonical category names and URN prefix. Baseline 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's function: fetch the first ~100 Revit elements of a given category with specific fields (objectid, name, externalId, property bag). It explicitly distinguishes from siblings by noting it is for category filtering rather than free-text search, and contrasts with revit_run_schedule for tabular views. This is a specific verb+resource+scope.

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?

Provides explicit 'When to use' and 'When NOT to use' sections, including a prerequisite (translation must be complete with manifest.status success) and direct alternatives (use revit_run_schedule for tabular views). This fully guides tool selection and execution timing.

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

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

With no annotations, the description carries full burden and discloses read-only nature, idempotency, APS scopes, rate limits, and error codes. This goes beyond basic expectations and sets clear expectations for behavior and side effects.

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 organized with labeled sections and front-loaded with the core purpose. While it includes lengthy rate limit and error details, these are structured and relevant, though slightly verbose. Each sentence earns its place in the context of a no-annotation 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?

The description covers purpose, use cases, return values, side effects, scopes, rate limits, and errors. For a tool with no output schema, it fully explains what to expect and how to handle failures, making it contextually complete.

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 already provides 100% coverage with detailed descriptions of each parameter, including how category is ignored when element_id is supplied. The description adds no new parameter semantics beyond the schema, so the baseline score 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 enumerates Revit parameters (type + instance) for a category or single element, and returns unique values with element counts. It distinguishes itself from revit_get_elements which returns elements themselves, making the purpose unambiguous.

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?

Explicit 'When to use' and 'When NOT to use' sections specify the ideal use case (schema discovery for schedules) and explicitly point to revit_get_elements for element retrieval. This provides clear guidance on alternatives and exclusions.

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

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

With no annotations provided, the description carries the full burden and delivers: APS scopes (data:read, viewables:read), rate limits, error responses with specific status codes and remedies, and side effects ('Read-only. Idempotent.'). This richly discloses behavior, going far beyond minimal mutation safety to include operational expectations.

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 uses labeled sections (When to use, When NOT to use, APS scopes, Rate limits, Errors, Side effects) that front-load the most important information. While it is longer than average, every sentence provides actionable detail without 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 simple one-parameter list operation, the description is complete: it explains what will be returned (sheet number + name), when to use it, how to avoid misusing it, auth scopes, errors, and side effects. No output schema exists, but the description sufficiently covers return values. The absence of pagination notes is a minor gap but does not undermine usability for an AI agent.

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 already fully documents model_id with pattern, examples, and description (coverage 100%). The tool description adds context about the URN being for a 'translated Revit model' but does not introduce new parameter-level syntax or constraints beyond the schema. Thus a baseline 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 opens with 'Enumerate the drawing sheets (title blocks with sheet number + sheet name like 'A-101: First Floor Plan')' which precisely identifies the action and resource. It also explicitly contrasts with sibling tool revit_get_views by stating 'this returns only 2D sheet entries', making the purpose unambiguous and well-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?

The description provides explicit 'When to use' and 'When NOT to use' sections, naming the exact alternative tool (revit_get_views) for model views. This is the highest level of usage guidance, clearly stating conditions for invocation and exclusions.

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

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

Without annotations, the description carries the full burden and excels: it discloses APS scopes needed, rate limits, error codes with remediation, and explicitly states 'Read-only. Idempotent.' This far exceeds minimal behavioral disclosure.

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 well-structured with clear labels and front-loads the most critical usage info. However, it includes some generic APS/OSS rate-limit details not directly relevant to this tool, making it slightly longer than necessary without harming clarity.

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?

Given the lack of an output schema, the description adequately covers return value structure, error handling, and side effects. It leaves no major gaps for a read-only list operation, making it highly complete.

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 schema already provides thorough documentation for model_id (base64url URN, pattern, example, description). The tool description adds no additional parameter semantics beyond stating the model is translated. Baseline 3 is appropriate since schema coverage is 100%.

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 returns every 2D and 3D view from a translated Revit model, listing specific view types and output fields (GUID, name, role, master view status). It explicitly distinguishes from sibling tools like revit_get_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?

Provides explicit 'When to use' and 'When NOT to use' sections, naming specific alternatives (revit_get_sheets, revit_get_elements, revit_run_schedule) and conditions for exclusion. This is exemplary usage guidance.

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

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

With no annotations provided, the description carries the full burden and excels by disclosing APS scopes, rate limits, error codes, side effects ('Read-only. Idempotent'), and operational behavior (matching by keyword, up to 15 shared parameters). This goes well beyond basic requirements.

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 long but every sentence earns its place, with clear section headers ('When to use', 'When NOT to use', 'APS scopes', 'Rate limits', 'Errors', 'Side effects'). It is well-organized and front-loaded with the most critical usage guidance, making it easy to scan.

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?

Given the lack of annotations and output schema, the description covers the essential context: scopes, rate limits, error handling, side effects, and input semantics. The only minor gap is a precise return format, but 'tabular, spreadsheet-style schedule' communicates the output nature sufficiently.

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 already provides complete descriptions for both parameters (100% coverage), and the description's mention of 'rows = elements matching a keyword' slightly reinforces the schedule_name semantics without adding new information. Since the schema covers everything, a baseline score 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 states a precise action ('Build a tabular, spreadsheet-style schedule') with clear resource and output format ('rows = elements matching a keyword, columns = up to 15 shared parameters'). It also explicitly distinguishes itself from siblings by naming when not to use alternatives, such as revit_get_elements and revit_get_parameters.

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 provides explicit 'When to use' and 'When NOT to use' sections, listing concrete use cases (Door Schedules, Wall Schedules, Room Schedules, QA/QC exports) and naming alternative tools for raw metadata and parameter schema. This fully clarifies when this tool should be selected over siblings.

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

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

With no annotations, the description fully carries the transparency burden. It discloses side effects (creates a transient bucket, uploads, starts translation), non-idempotency ('NOT idempotent — each call creates a fresh bucket and new URN'), rate limits, and detailed error handling. This is exemplary behavioral disclosure.

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 well-structured with clear section headings (When to use, When NOT to use, APS scopes, Rate limits, Errors, Side effects). Every sentence contributes actionable information; it is long but not verbose. The front-loaded usage guidelines make it easy to navigate.

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?

Despite no output schema, the description explains the full processing pipeline, side effects, rate limits, error scenarios, and downstream consequences. It even implies the output (a new URN) through side-effect disclosure. For a tool of this complexity, the description is thorough and self-sufficient.

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 schema already fully documents all parameters. The description adds only a general mention of the 100MB size limit (already present in the file_url schema description) and does not provide new parameter semantics beyond the schema. Baseline 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's function: 'Ingest a Revit (.rvt / .rfa / .rte / .rft) file... downloading it from a publicly reachable URL, uploading it to an OSS bucket, and starting an SVF2 translation'. This specific verb+resource+process makes it easily distinguishable from sibling tools like revit_get_elements, which are read-focused.

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?

Explicit 'When to use' and 'When NOT to use' sections are provided, with concrete exclusions (e.g., 'Do not call if you already have a translated URN') and a direct alternative ('use the existing model_id instead'). Also mentions the downstream benefit for revit_* tools, giving clear contextual guidance.

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