bulk_job_results

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

Goes well beyond the annotations by disclosing the default output path, the symlink restriction on the result folder (and that parent symlinks are unchecked), the absolute-path requirement, and the no-clobber rule. Critically, it reconciles readOnlyHint=false by clarifying 'Read-only in the org; writes local CSV files' — explaining exactly why the write hint is set despite no org mutation.

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?

Four sentences, front-loaded with the core action and output location before the constraints. Dense but each sentence earns its place except the parent-symlink caveat, which is marginally over-detailed for a tool description.

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 single-parameter tool with no output schema, the description covers purpose, output destination, constraints, and return values, so an agent can invoke it correctly. It stops short of addressing job-state error handling or large-result behavior, but nothing essential is missing.

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 documents all three nested parameters (jobId pattern/source, outputDir constraints, targetOrg default), so the description mostly restates outputDir behavior rather than adding new semantics. It adds the concrete default location '<home>/salesforce-bulk-results/<jobId>/' but says nothing about jobId or targetOrg beyond the 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?

States a specific verb and resource: 'Write the successful, failed and unprocessed records of a finished Bulk API 2.0 job to CSV files,' and names the return value (paths and row counts). The 'finished job' qualifier plus the CSV-to-disk framing distinguishes it from siblings like bulk_job_status or query_records_to_file without opening a schema.

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 prerequisite that the job must be 'finished' is stated, implicitly routing agents to bulk_job_status first, and the schema notes jobId comes from a bulk_* tool. However, no explicit alternatives or when-not-to-use conditions are given; the agent must infer the sequencing itself.

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