jig_perfUsed by an open jig to report how fast it loaded. You do not need to call this.
| Name | Required | Description | Default |
|---|---|---|---|
| jigId | Yes | The jig's id, as `jig_open` or `jig_list` returned it. | |
| report | No | How long this open took to load, and which calls failed and why. |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | No | True when the report was recorded. | |
| message | No | Why the call failed, when `ok` is false. |
Changes observed during successful MCP inspections.
Input schema / properties / jigId / descriptionAdded value: +"The jig's id, as `jig_open` or `jig_list` returned it."Input schema / properties / report / descriptionAdded value: +"How long this open took to load, and which calls failed and why."Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "properties": {
+ "message": {
+ "description": "Why the call failed, when `ok` is false.",
+ "type": "string"
+ },
+ "ok": {
+ "description": "True when the report was recorded.",
+ "type": "boolean"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false and openWorldHint=false; the description's claim that it is called automatically by an open jig is consistent with the non-read-only, idempotent profile. It adds no detail on what is written, whether failures are retried, or how the report payload is shaped, so it adds only modest value beyond the annotations.
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 short sentences with zero filler, and the caller identity is front-loaded before the opt-out instruction. Nothing could be removed without losing meaning.
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?
For a two-parameter telemetry tool with a full schema and an output schema, the description covers what an agent needs: what it is and that it is not required. Only a note on when an agent would ever invoke it (debugging a slow open) 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?
Schema description coverage is 100%, and the description adds nothing about jigId or the report object beyond what the schema already says. Baseline 3 applies since the schema carries the parameter burden entirely.
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 function — reporting load performance back to the jig runtime — and implicitly distinguishes itself from the user-facing jig_* tools by naming 'an open jig' as the caller. It is not a tautology of the name, though 'jig_perf' alone would not have conveyed the telemetry meaning.
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?
Provides an explicit exclusion: 'You do not need to call this,' which is exactly the guidance an agent needs to skip the tool. It does not, however, name a condition under which an agent might legitimately need it (e.g. debugging) or point to a sibling for that purpose.
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.