salesforce_composite_graph

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

Annotations already carry the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false, openWorldHint=true), and the description does not contradict them. The description adds useful context beyond annotations by disclosing that execution is indirect (routes through a domain-agent dispatcher) and scoped by JWT, tenant, and company. It does not elaborate on what the destructive behavior affects or what side effects may occur.

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 compact and front-loaded: the action name and verb appear first, followed by the routing note and the two Args lines. No sentence is wasted or redundant with the schema. It is under-specified in substance, but that is a completeness issue rather than a structure/conciseness one.

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 generic dispatcher wrapper with an opaque action name, the description is materially incomplete: it never says what composite_graph accomplishes, what kinds of objectives fit the message param, what belongs in inputs, or when this tool applies instead of salesforce_chat/dispatch_domain_agent. The presence of an output schema reduces the need to explain return values, but the core invocation decision is left entirely to the agent's guesswork.

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 0%, so the description must compensate, and it partially does: it defines message as a 'Free-text objective' and inputs as an 'Optional JSON string of structured inputs.' However, this is minimal compensation — there is no guidance on valid keys inside the inputs JSON, how message and inputs interact, or any example. The parameter semantics are just bare one-liners that barely exceed the schema's type/default information.

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 specific verb and resource ('Run the salesforce domain agent action composite_graph') and adds the routing mechanism, so it is not a pure tautology. However, it never explains what the composite_graph action actually does, leaving the agent unable to distinguish its outcome from generic siblings like dispatch_domain_agent, salesforce_chat, crm_chat, or salesforce_product_graph_query. The purpose is clear at the mechanism level but vague at the functional level.

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 only contextual hint is that the call 'Routes through the platform's domain-agent dispatcher under your JWT, tenant, and company scope,' which describes the execution path but not when an agent should choose this tool. No when-to-use conditions, exclusions, or alternative tool names are given despite a sibling list containing dispatch_domain_agent, invoke_tool, and dozens of salesforce/CRM actions. An agent has no basis for selecting this over its alternatives.

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