Skip to main content
Glama
Sign In

Joeb

by com.joebapp
OverviewDiscussionsAdmin

List blocked companies

list_blocked_companies
Read-only

List the companies the user has blocked, most recently blocked first, one line each.

search_jobs leaves out every posting from a blocked company. Each line is: [block {id}] {company} ({source}) · blocked {date} {company} is the company's name as the job it was blocked from showed it, {source} the job board its postings come from (greenhouse, ashby, lever...), and {date} the day it was blocked (UTC). unblock_companies takes the number in brackets, the block id, which is not a job id. A company is blocked on its own job board only: the same employer posting on another board is a separate company, not blocked by this one.

When the user has blocked no company, the reply says so.

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": "list_blocked_companies"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare a safe read, so the bar is low, yet the description adds substantial behavior: exact line format, ordering, UTC dating, empty-result messaging, and the key semantic that a block id is not a job id. It also discloses that blocking is per job board, so the same employer on another board is not blocked — a non-obvious rule an agent could otherwise get wrong.

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?

Front-loaded with the purpose and ordering, then the output template, then field definitions, then edge cases — a logical progression. The literal line-format block with indentation is slightly awkward in prose, and the source-board examples are a touch verbose, but nothing is filler.

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

Completeness5/5

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

There is no output schema, so the description must carry the return format — and it does, down to the exact per-line template and field meanings. The empty-result case and cross-tool id semantics are also covered, leaving nothing an agent needs to call this correctly.

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?

The tool takes zero parameters, so the baseline is 4. The description still clarifies the meaning of a value surfaced in the output (the block id, consumed by unblock_companies), which is useful downstream context even though it is not an input.

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?

States a specific verb and resource ('List the companies the user has blocked') plus ordering ('most recently blocked first') and output shape ('one line each'). An agent can immediately distinguish this from siblings like get_jobs or list_saved_jobs.

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?

Explains the relationship to siblings: search_jobs omits blocked companies, and unblock_companies consumes the bracketed block id. This gives clear context for when the tool matters, though it stops short of an explicit 'use this when the user asks what is blocked' trigger or any when-not guidance.

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

All Joeb toolsInspect
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