list_historyThe versions of a presentation you can see, newest first: number, who made it (person and agent), when, and what changed. Changes of one author in a row within 10 minutes are one version.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The presentation's slug (its address: /movie/<slug>/). | |
| limit | No | At most this many (default 50). |
| Name | Required | Description | Default |
|---|---|---|---|
| versions | Yes |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "versions": {
+ "items": {
+ "properties": {
+ "agent": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "author": {
+ "type": "string"
+ },
+ "changes": {
+ "description": "What changed in this version.",
+ "items": {
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "created_at": {
+ "description": "ISO 8601 date and time.",
+ "type": "string"
+ },
+ "number": {
+ "type": "integer"
+ },
+ "updated_at": {
+ "description": "ISO 8601 date and time.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "number"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "versions"
+ ],
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish the safe-read profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower, and the description clears it by disclosing ordering (newest first) and a non-obvious aggregation rule — consecutive edits by one author within 10 minutes collapse into a single version. That coalescing rule is real behavioral information an agent could not infer from the schema.
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; the ordering and field list come first and the subtle aggregation rule lands as the second sentence. Every clause earns its place.
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?
With an output schema present, return shape needn't be explained, and visibility scoping plus the aggregation rule are covered. The one gap is workflow linkage: nothing says the version numbers returned here feed get_version or restore_version, which matters in a 27-tool sibling set.
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 100%, so slug and limit are already documented with their defaults. The description adds nothing about limit or truncation behavior, so baseline 3 is appropriate — it neither compensates for a gap nor duplicates the schema harmfully.
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 names the resource precisely — the version history of a presentation — and even enumerates the returned fields (number, author, timestamp, change summary). It stops short of distinguishing itself from the sibling get_version, so an agent still has to guess which of the two it wants for a single-version lookup.
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?
Usage is only implied: 'you can see' and 'newest first' suggest a browsing/audit view over the presentation's past. There is no explicit when-to-use or when-not, and no sibling (get_version, restore_version) is named as the alternative for a single version or a rollback.
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.