Skip to main content
Glama
Aggrete

aggrete

Official
by Aggrete
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Check a plan against the code of conduct

aggrete__check

Check whether a sequence of tool calls is allowed before executing any. Get the decision, applicable rule, clause, and remediation to answer 'can I do X?' questions.

Instructions

Ask whether a sequence of tool calls would be allowed before running any of them. Returns the decision (allowed, allowed-with-alert, or refused), the rule that applies, its clause, and the remediation. Nothing is fetched. Use this to answer 'can I do X?' questions: translate the request into the tool calls it would take, then pass them as tools in order.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toolsYesThe tool calls you are considering, in order, by their exact names on this server, e.g. ["hr__recent_joiners", "finance__budget_roles"]. To check a call by its arguments (e.g. an export's scope), pass an object instead of a name: {"tool": "crm__export", "args": {"scope": "all"}}.
entitiesNoOptional. The people the plan concerns, as p:<email> ids, applied to each read. Omit to evaluate assuming the calls concern the same people (you and a colleague).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / tools / description
      Previous value: -"The tool calls you are considering, in order, by their exact names on this server, e.g. [\"hr__recent_joiners\", \"finance__budget_roles\", \"hr__leave_balance\"]."New value: +"The tool calls you are considering, in order, by their exact names on this server, e.g. [\"hr__recent_joiners\", \"finance__budget_roles\"]. To check a call by its arguments (e.g. an export's scope), pass an object instead of a name: {\"tool\": \"crm__export\", \"args\": {\"scope\": \"all\"}}."
    • addedInput schema / properties / tools / items / oneOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "properties": {
+      "args": {
+        "type": "object"
+      },
+      "tool": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "tool"
+    ],
+    "type": "object"
+  }
+]
    • removedInput schema / properties / tools / items / type
      Removed value: -"string"
  2. Added

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral disclosure burden and does so well: it states the tool makes no fetch, returns a decision with the applicable rule/clause/remediation, and is intended to be called before executing anything. It does not discuss auth or rate limits, but the side-effect and return contract are the key disclosures for this kind of policy-checking tool.

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?

The description is compact and front-loaded: it opens with the core behavior, then the return contract, then the practical usage instruction. Every sentence earns its place without repeating the title or schema.

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?

Despite having no output schema, the description enumerates the key return fields (decision, rule, clause, remediation) and covers the intended use of both parameters. For a two-parameter policy-checking tool, this is sufficient for an agent to select and invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100%, the description adds actionable meaning beyond the schema: pass calls in order, use exact server names, and pass objects with args to check calls by their arguments. It also clarifies the optional `entities` behavior by explaining that omitting it evaluates assuming the calls concern the same people.

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 a specific operation—checking whether a sequence of tool calls would be allowed—and specifies the result categories (allowed, allowed-with-alert, refused) plus the returned rule, clause, and remediation. It also distinguishes itself from data-fetching siblings by explicitly stating 'Nothing is fetched.'

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 when-to-use guidance: answer 'can I do X?' questions before running any calls, and it explains how to construct input by translating the request into ordered tool calls. It does not explicitly name alternative tools or exclusions, though 'Nothing is fetched' implies it is not a data-retrieval tool.

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

Deploy Server

Other Tools