Skip to main content
Glama
HyperRouteAI

hyperroute-mcp

Official
by HyperRouteAI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

declare_my_tool

Register an existing tool so HyperRoute routes matching tasks to it by name. Provide verbatim trigger phrases that decide when your tool is used.

Instructions

Declare a tool the USER already has, so HyperRoute routes to it by name when they said to. Call this when the user says something like "I have my own web search, always use it for research", "we have an internal API for X", or "use my VPN tool whenever I need to connect".

triggers is the whole thing, and it is REQUIRED: the sentences saying WHEN to use the tool, kept verbatim in the user's own words and language. Pass what they actually said — "for invoices go through my Xero thing", "mp3s over two minutes go to Olena's transcriber", "use it whenever I need to do a VPN connect". Do not tidy it into a category, do not translate it, and do not drop a condition ("only if the file is in Japanese" is part of the trigger). That sentence is read against every incoming query, and it is what decides whether their tool wins. A tool may carry several triggers; pass them all.

description is optional free text about what the tool is. capabilities is optional too — named regions used only to word the user's own outcome report, never to route. Leave both empty unless the user gave you something to put there; a declaration with a trigger and nothing else is complete.

stance — "pinned" (default) means their tool wins whenever a trigger fires; "benchmarked" lets a catalog tool displace it once the user's own reported outcomes show it underperforming. Start pinned; that is what the user asked for.

When NO trigger fires the tool is simply not in the ranking, so a declaration is never a blanket override. Nothing here is scored — HyperRoute has never tested their tool and never claims to have.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
stanceNopinned
triggersYes
project_idNo
descriptionNo
capabilitiesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.0

TDQS

A4.2/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it explains routing semantics (triggers decide whether the tool wins), the pinned vs benchmarked disposition, that no trigger means the tool is not ranked at all, and that nothing is scored or tested. That is exactly the behavioral context an agent needs for this tool.

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 action and the required argument, and the repeated 'do not tidy it / do not translate it / do not drop a condition' instructions earn their space given how fragile verbatim triggers are. Slightly long, but little is deletable without losing meaning.

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 6-parameter, no-output-schema declaration tool with zero annotation coverage, the description supplies the routing semantics, argument semantics and defaults needed to call it correctly. Only the name and project_id parameters are left to the agent's inference.

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 description coverage is 0%, so the description must compensate, and it thoroughly explains triggers, stance, description and capabilities. It leaves name (required) and project_id undocumented, which is the only gap in an otherwise strong parametric explanation.

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?

States a specific verb and resource ('Declare a tool the USER already has') plus the downstream effect ('HyperRoute routes to it by name'). The verb set over siblings (update_my_tool, remove_my_tool, my_tools) is easy to infer, so it is distinguishable, though it never names an alternative explicitly.

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?

Gives concrete trigger phrasing for when to call ('I have my own web search, always use it for research') and clarifies that a declaration with only a trigger is complete. It stops short of stating when NOT to declare, e.g. how this differs from prefer_tool or when a declaration should be replaced by update_my_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