connector_salesforce_bulk_ingest_close

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true, so the bar for additional behavioral context is lower. The description adds useful governance context about routing through the governed connector authority and notes that approval_ref is needed 'when resuming a write.' However, it does not explain what destructive effect occurs when closing a bulk ingest job, leaving the agent to infer the consequences.

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 the parameter list is easy to scan. The only redundancy is the opening line repeating 'Salesforce connector operation' and 'platform tool salesforce.bulk_ingest_close,' which could be trimmed, but overall the structure is efficient.

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?

All parameters are described and the output schema exists, but the core operational context is missing: what closing a bulk ingest job does, when in the lifecycle it should be invoked, and what side effects to expect. Given the destructive annotation and the surrounding bulk ingest siblings, this is a significant gap that parameter and annotation coverage do not fill.

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%, but the description fully compensates by defining all seven parameters with meaningful semantics: arguments as a JSON string, project_id as an authenticated UUID, idempotency_key as a stable business-action identity, and approval_ref as a write-resumption approval UUID. This is exactly the value the input schema lacks.

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 identifies the operation as `salesforce.bulk_ingest_close` and labels it a Salesforce connector operation, but it never states what closing a bulk ingest job actually does — e.g., finalizing the ingest, preventing further uploads, or triggering result processing. It leans on the name's 'close' rather than explaining the tool's function, and it does not differentiate itself from sibling bulk ingest tools beyond the name.

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?

There is no guidance on when to use this tool versus the closely related connector_salesforce_bulk_ingest_create, upload, status, or results tools. The only usage-related sentence, 'Routes only through the exact project/account governed connector authority,' is a routing constraint, not a selection criterion. An agent has no help deciding that this is the tool to call after an upload or before retrieving results.

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