EaseWeb

Change a project

update_project

Change a project of yours: its title and description, which presentations are in it ("add" puts presentations of yours at its end, "remove" makes them presentations on their own again) and their order ("order": the slugs of all of its presentations). Links between presentations work only inside a project: a removed presentation's links to the others stop leading anywhere. Access: "access" is the level of the project, which its presentations inherit (the stricter of the project's and the presentation's own level counts); "grant" gives people access to all of it ({"user": name, "role": "view"|"edit"}), "revoke" takes it away (user names).

Input Schema

TableJSON Schema

Name	Required	Description
`add`	No	Slugs of presentations.
`grant`	No	Give access to the whole project: [{"user": <user name>, "role": "view"\|"edit"}].
`order`	No	Slugs of all the presentations of the project, in the new order.
`title`	No	New title.
`access`	No	Level of the project: "open", "public" or "private".
`remove`	No	Slugs of presentations.
`revoke`	No	User names whose access is taken away.
`project`	Yes	The project's slug (its address: /project/<slug>/).
`description`	No	New description.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	Yes
`url`	No	The address people open in a browser.
`role`	No	owner, edit, view or null.
`slug`	Yes	The address of the project: /project/<slug>/.
`owner`	No
`title`	Yes
`access`	No	open, public or private: inherited by its presentations.
`grants`	No	Who was given access (the owner sees it).
`is_owner`	No
`description`	No
`presentations`	No	Its presentations, in order.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 29, 2026

addedInput schema / properties / access

Added value: +{
+  "description": "Level of the project: \"open\", \"public\" or \"private\".",
+  "enum": [
+    "open",
+    "public",
+    "private"
+  ],
+  "type": "string"
+}

addedInput schema / properties / grant

Added value: +{
+  "description": "Give access to the whole project: [{\"user\": <user name>, \"role\": \"view\"|\"edit\"}].",
+  "items": {
+    "type": "object"
+  },
+  "type": "array"
+}

addedInput schema / properties / revoke

Added value: +{
+  "description": "User names whose access is taken away.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / access

Added value: +{
+  "description": "open, public or private: inherited by its presentations.",
+  "type": "string"
+}

addedOutput schema / properties / grants

Added value: +{
+  "description": "Who was given access (the owner sees it).",
+  "items": {
+    "properties": {
+      "role": {
+        "type": "string"
+      },
+      "since": {
+        "description": "ISO 8601 date and time.",
+        "type": "string"
+      },
+      "user": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

AddedSep 29, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations declare readOnly=false, destructive=false, idempotent=false, so the safety profile is covered; the description adds genuine context beyond them: links between presentations only work inside a project and a removed presentation's links stop leading anywhere, and access is inherited with the stricter of project/presentation levels winning. "remove" being re-parenting rather than deletion is consistent with destructiveHint=false. Error/conflict behavior on duplicate slugs or invalid order is still unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every clause carries semantics, and the tool's core action is front-loaded. However it is delivered as one dense run-on paragraph with nested quotes and parentheses, mixing several parameters in prose, which hurts scannability for an agent parsing parameter behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

All nine parameters are addressed and an output schema exists, so return values need not be explained. For a mutation tool, what remains thin is preconditions (what role the caller needs) and failure modes, but the operational semantics of every mutator are otherwise covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds real meaning on top: "order" must contain the slugs of ALL the project's presentations, "add" appends at the end, "remove" re-parents rather than deletes, and "access" is inherited by presentations under a strictest-wins rule. "grant" role format is repeated from the schema, which adds little.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a concrete verb+resource ("Change a project of yours") and enumerates the mutable facets: title, description, contained presentations, their order, and access. The scope is precise, though it never names update_presentation, the sibling whose title/description editing overlaps, leaving the boundary to be inferred.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage of each sub-operation is described functionally ("add" puts presentations at its end, "remove" makes them presentations on their own), so the semantics of each mode are implied. But there is no explicit when-to-use guidance, no statement of prerequisites (e.g. the caller's own role on the project), and no routing to update_presentation vs. set_access for overlapping needs.

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

All EaseWeb tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?