Koskamo

Answer an issue on your MCP listing

koskamo_update_mcp_issue

Destructive

For the owner of a listing: respond to one reported issue. acknowledge replies publicly; wont_fix declines with a public reason; fixed requires a public note and is accepted only when a live check of the endpoint passes at that moment. Reporters see your response through their receipts.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>",
      "owner_key": "<owner_key>",
      "issue_id": "<issue_id>",
      "resolution": "<resolution>"
    },
    "name": "koskamo_update_mcp_issue"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	The listing id returned at registration
`issue_id`	Yes	Issue id from the owner issue list
`response`	No	Public reply shown with the issue; required for wont_fix and fixed
`owner_key`	Yes	The owner key issued when the listing was published; verified for this listing and omitted from the response
`resolution`	Yes	acknowledge, wont_fix or fixed

Output Schema

Name	Required	Description	Default
`issue`	No
`trust`	No
`issues`	No
`server_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true, idempotentHint=false and openWorldHint=true, but the description adds substantive behavior the annotations cannot express: fixed is conditionally accepted based on a live check at that moment, and wont_fix requires a public reason. The 'Reporters see your response through their receipts' line discloses downstream visibility, which matters for a public mutation. It does not say what happens when the live check fails or whether a resolution can be amended later.

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

Conciseness5/5

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

Three sentences, no padding, and the audience constraint is front-loaded before the resolution semantics. The compressed semicolon clause efficiently encodes three distinct modes without repeating the schema.

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?

Output schema exists, so return values need no explanation, and the description covers what is otherwise invisible: gating conditions, required public text, and reporter visibility. It leaves error behavior unspecified (e.g. what a failed live check means for the caller), which is the main remaining gap for a destructive, non-idempotent mutation.

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, but the description adds real meaning beyond the schema's plain enum listing by explaining the consequence of each resolution value (public reply, public decline, live-check gating). The response/owner_key parameters are still left to their schema descriptions, so it is not a full 5.

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?

The description names a specific verb and resource ('respond to one reported issue') and scopes the audience ('For the owner of a listing'), which implicitly separates it from the reporter-side report_mcp_issue and from get_mcp_issue_status/list_mcp_issues. It stops short of naming any sibling tool, so the differentiation is inferred rather than stated.

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

Usage Guidelines4/5

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

It gives clear per-mode guidance: acknowledge for public replies, wont_fix for declining with a public reason, fixed only when a live endpoint check passes at that moment. That is genuinely actionable selection logic within the tool's own enum. There is no explicit when-not-to-use or pointer to the sibling that supplies the issue_id (only the schema hints at 'owner issue list').

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

All Koskamo 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?