Salesforce MCP Server

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

The annotations already declare readOnlyHint=true, indicating a safe read operation. The description adds valuable context beyond this by specifying the scope of metadata returned (fields, relationships, picklist values, record types) and listing common field types and standard/custom object naming conventions, which helps the agent understand what to expect without contradicting 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 efficiently structured: the first sentence states the purpose and usage guideline, followed by specifics on metadata content and examples. Every sentence adds value without redundancy, making it easy to parse and front-loaded with key 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?

Given the tool's complexity (metadata retrieval with rich output), the description is complete enough: it details what metadata is returned, provides usage context, and lists examples, compensating for the lack of output schema. With annotations covering safety, no critical gaps remain for agent decision-making.

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?

With 0% schema description coverage and only one parameter, the description compensates by providing semantic context: it implies the parameter is a Salesforce object name (e.g., 'Account' or custom object ending in '__c'), though it doesn't explicitly name the parameter or detail syntax. This adds meaningful guidance beyond the bare schema.

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 specific action ('Get complete metadata') and resource ('for a Salesforce object'), distinguishing it from siblings like list_objects (which lists objects) or get_record (which retrieves data records). It explicitly mentions what metadata is included: fields, relationships, picklist values, and record types.

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 guidance on when to use this tool ('Call this before querying or writing to an unfamiliar object'), distinguishing it from query/write tools like run_soql_query or create_record. It also implies when not to use it (for familiar objects or direct data operations).

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