Skip to main content
Glama

sockdock_test_match

Read-only

Check which SockDock rule would match a Slack post and what the program would receive, using channel, text, optional user and mention, without posting to Slack.

Instructions

Tells which rule would run for a post with the given text in the given channel, taking the order of rules and rules that are off into account, and what a program would receive as values. Use channel dm for a DM to the Slack app, and mention: true for a post that mentions the Slack app (rules with mention_only need it). Pass user (a member ID) to also skip rules that person may not run; without it, who posts is ignored and allowed_users in the result tells you the matched rule is limited to some people. Use it after creating or changing a rule to check the condition, or when the user asks why a post did or did not trigger a rule. It does not post anything to Slack and does not check whether the channel's posts reach SockDock (use sockdock_check_rule for that).

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": {
      "channel": "<channel>",
      "text": "<text>"
    },
    "name": "sockdock_test_match"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesthe post's text
userNothe poster's Slack member ID (from sockdock_find_users); rules this person may not run are passed over, as for a real post. Omit to ignore who posts
channelYeschannel name (#dev-help or dev-help) or ID; must be in sockdock_list_channels. dm for a DM to the Slack app
mentionNotrue when the post mentions the Slack app (@app); rules with mention_only run only then

Output Schema

NameRequiredDescriptionDefault
ruleNo
valuesNowhat the rule would pass to a program (text, or the regular expression's named groups)
matchedYes
allowed_usersNomember IDs of the only people who may run the matched rule; a post by anyone else does nothing (or goes to a later rule)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description still earns credit by stating it posts nothing to Slack, that evaluation honors rule ordering and off rules, and that omitting user means the poster is ignored and the allowed_users field in the result reveals an allow-list restriction. It stops short of describing output shape or edge cases like an empty rule set, which the output schema largely covers anyway.

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?

One dense paragraph that front-loads purpose before parameters and alternatives; nearly every clause carries information. It would read better split into purpose / parameters / when-not-to-use, but there is little 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?

For a read-only simulation tool with a full output schema, the description covers the semantics of matching (ordering, disabled rules, mention_only, user eligibility), the meaning of every non-obvious input convention, and the boundary against the nearest sibling. Nothing an agent needs to invoke it correctly is missing.

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 prose goes further than the schema on `user`: it explains the consequence of omission (poster ignored) and how the returned allowed_users field signals that the match is limited to particular people. The dm and mention guidance mirrors the schema descriptions rather than adding to them, so this is a modest step above baseline.

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 opening clause names a specific verb and resource: it reports which rule would run for a given post text in a given channel, accounting for rule order and disabled rules, plus the values a program would receive. That framing ('would run', i.e. a dry-run match) is unmistakable and distinguishes it from mutation siblings like sockdock_save_rule and sockdock_set_rule_enabled.

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

Usage Guidelines5/5

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

It gives explicit triggers ('after creating or changing a rule to check the condition, or when the user asks why a post did or did not trigger a rule') and an explicit exclusion with the right alternative: it does not verify whether a channel's posts reach SockDock, and sockdock_check_rule should be used for that.

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