Create a projector display screen for a published tournament
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Display name (default: Main screen) | |
| token | No | URL token (default: auto-generated) | |
| tournament_id | Yes | Tournament ID |
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Display ID | |
| name | Yes | Display name | |
| token | Yes | URL token; anybody who has it can open the screen | |
| display_url | Yes | JSON feed the screen reads | |
| projector_url | Yes | The page to open on the projector |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "display_url": {
+ "description": "JSON feed the screen reads",
+ "type": "string"
+ },
+ "id": {
+ "description": "Display ID",
+ "type": "string"
+ },
+ "name": {
+ "description": "Display name",
+ "type": "string"
+ },
+ "projector_url": {
+ "description": "The page to open on the projector",
+ "type": "string"
+ },
+ "token": {
+ "description": "URL token; anybody who has it can open the screen",
+ "type": "string"
+ }
+ },
+ "required": [
+ "id",
+ "name",
+ "token",
+ "display_url",
+ "projector_url"
+ ],
+ "type": "object"
+}Input schema / properties / session_tokenRemoved value: -{
- "description": "The session_token returned by create_tournament",
- "type": "string"
-}Input schema / requiredPrevious value: -[
- "tournament_id",
- "session_token"
-]New value: +[
+ "tournament_id"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered by structured data. The description adds the 'published tournament' precondition, which is real behavioral context. It does not say what happens on a duplicate name/token, whether creation fails when the tournament is unpublished, or what the response contains.
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 sentence with no filler, front-loaded with the verb and resource. It is appropriately sized for the tool's simplicity, though it is terse enough to leave questions unanswered.
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 values need not be described, and annotations cover the safety profile. The gap is failure/edge behavior: the stated 'published tournament' precondition is never explained in terms of consequences, and non-idempotency (per annotations) is not surfaced in the description.
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%, and the schema already documents name, token (with auto-generation defaults), and tournament_id. The description adds no parameter-level detail beyond that, 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?
The description names a specific verb (Create) and a specific resource (projector display screen), plus a scoping condition (for a published tournament). That distinguishes it from siblings like create_tournament, create_stage, or add_court. It stops short of naming an alternative, but the resource 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?
'For a published tournament' implies a precondition that the agent must create/publish the tournament first, which is genuine usage guidance. However, there is no explicit when-to-use vs. alternative, and no statement of what to do when the precondition is unmet.
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.