Skip to main content
Glama
mcp-feature-test

mcp-feature-test

by linuxrrze

Change the server’s lists (list_changed)

change_lists

Add, remove, or reset dynamic tools, prompts, and resources, then send list-changed notifications to verify client lists update automatically.

Instructions

Add or remove a dynamic tool (dynamic_tool_N), prompt (dynamic_prompt_N) and resource (test://dynamic/N), at most 3 each, and send the matching notifications/*/list_changed. Then check whether the client’s tool, prompt and resource lists update by themselves. The lists are shared by all clients of this server; action=reset removes every dynamic item.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "change_lists"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoWhich list to changeall
actionNoadd the next item, remove the newest one, or reset everythingadd

Output Schema

NameRequiredDescriptionDefault
actionYes
atLimitYes
changedYes
dynamicYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With readOnlyHint=false and idempotentHint=false already declaring this is a non-idempotent write, the description still adds real value: the 3-items-per-kind cap, the shared-across-all-clients state, and the fact that action=reset wipes every dynamic item. It does not say what happens when the cap is exceeded (error vs. no-op), which keeps it below 5.

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?

Three sentences, front-loaded with what gets changed and the cap, followed by the notification effect and the shared-state caveat. The middle sentence about checking whether client lists update is slightly redundant given an output schema exists, but it is short and earns its place as intent context.

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?

For a two-parameter, zero-required mutation tool with an output schema and annotations covering safety, the description supplies the essential state model (capped, server-wide shared, reset is destructive). The only meaningful gap is error/edge behavior when adding beyond the limit of 3.

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% and both enums are documented, so the baseline is 3. The description adds beyond that by mapping each kind value to a concrete artifact name and by spelling out that action=reset is a full purge rather than a per-item removal, material semantics the enum labels alone do not convey.

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

Purpose5/5

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

The description names the resource (server list entries for tools/prompts/resources), the exact verb set (add/remove/reset), the concrete identifiers created (dynamic_tool_N, dynamic_prompt_N, test://dynamic/N), and the side effect (notifications/*/list_changed). That is specific enough to separate this mutation tool from siblings like update_live_resource or list_seen_clients without opening any schema.

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 is implied rather than stated: 'Then check whether the client's tool, prompt and resource lists update by themselves' signals this is a list_changed notification test harness, which tells the agent the context. But there is no explicit when-to-use/when-not, and no sibling is named as the alternative for non-dynamic changes.

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