bulk_statusStatus of one bulk job you own: state, attempt count and — when finished — the summary with produced count and per-row failures (row number + reason; failed rows never block the rest). Finished outputs stay downloadable for 7 days via the REST endpoint the response names.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | Job id from bulk_submit (32 hex characters; the dashed UUID form is accepted) |
Changes observed during successful MCP inspections.
Input schema / properties / job_id / descriptionPrevious value: -"Job id from bulk_submit"New value: +"Job id from bulk_submit (32 hex characters; the dashed UUID form is accepted)"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: attempt count is exposed, partial-failure semantics are explicit ('failed rows never block the rest'), and the 7-day output retention plus where to download ('the REST endpoint the response names') are disclosed. This is exactly the extra context the safety annotations cannot convey.
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?
A single front-loaded sentence that states the resource first, then the payload, then the failure and retention semantics. Every clause carries distinct information (state, attempts, produced count, per-row failures, 7-day window); nothing is padding.
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?
No output schema exists, so the description carries the return-shape burden and does so: it names the fields returned, explains partial failures and their non-blocking nature, and covers output retention and retrieval path. Nothing an agent needs in order to interpret the result 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?
With 100% schema description coverage, the schema already documents job_id's format (32 hex, dashed UUID accepted) and its origin in bulk_submit. The description only adds the ownership qualifier ('you own'), which is a marginal semantic addition, so baseline 3 applies.
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?
Specific verb+resource: 'Status of one bulk job you own', immediately scoped to a single job versus the plural sibling bulk_list. It then enumerates exactly what is returned (state, attempt count, summary), so an agent knows precisely what this call yields without opening the 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?
'One bulk job you own' implies the single-job case as opposed to bulk_list, and the schema ties job_id back to bulk_submit, so the usage context is inferable. However the description itself never names bulk_list or bulk_submit, nor states when-not to use it (e.g., before submission, or for enumerating jobs).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.