Read up to 3 file records per page, with formats, sizes, hashes and current download availability. Continue with the exact nextCursor until null.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| tool | No | ||
| limit | No | ||
| cursor | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / limit / minimumRemoved value: -1Output schema / additionalPropertiesRemoved value: -trueInput schema / properties / cursor / descriptionRemoved value: -"Page cursor returned by the previous read."Input schema / properties / id / descriptionRemoved value: -"Artifact or record id returned by a previous read."Input schema / properties / limit / descriptionRemoved value: -"Maximum number of returned rows; use the stated bounds."Input schema / properties / tool / descriptionRemoved value: -"Local runner or tool to select from the allowed choices."Input schema / properties / cursor / descriptionAdded value: +"Page cursor returned by the previous read."Input schema / properties / id / descriptionAdded value: +"Artifact or record id returned by a previous read."Input schema / properties / limit / descriptionAdded value: +"Maximum number of returned rows; use the stated bounds."Input schema / properties / tool / descriptionAdded value: +"Local runner or tool to select from the allowed choices."Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint=false, and the description is consistent with that read-only profile. It adds genuine context the annotations don't: the page size, the fields surfaced (formats, sizes, hashes, download availability), and the termination condition for paging. The only gap is the mismatch between 'up to 3 per page' and a schema limit that allows up to 500.
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?
Two dense sentences with no filler, and the primary behavior (paged read with rich fields) is front-loaded ahead of the continuation rule. Nothing is wasted, though the second sentence could be tightened.
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?
An output schema exists, so return-value explanation is optional and the field list is a bonus. However, for a 4-parameter tool with zero schema descriptions, the description leaves the required id and the tool filter entirely unexplained, and the 3-vs-500 limit discrepancy undermines correct invocation.
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 carry the parameter burden and it does not. It explains the cursor semantics well, but the required 'id' and the enum-constrained 'tool' filter are never mentioned, and 'up to 3 per page' conflicts with a limit parameter bounded at 500 — an agent cannot tell whether limit is honored or overridden.
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 (read file records) plus the per-page shape and returned fields, so an agent understands this is a paginated file listing. It never names what the records belong to or how it differs from sibling artifact-oriented tools, but the verb+resource pairing is unambiguous.
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 second sentence gives a concrete pagination protocol ('Continue with the exact nextCursor until null'), which is real usage guidance. There is no statement of when to call this versus siblings like get_artifact or search_artifacts, and no mention of what the required id identifies.
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.