Skip to main content
Glama

create_highlight

Creates a custom CS2 match highlight from explicit segments, a tick range with player POV, or auto-clipped round kills; returns the highlight spec for later rendering.

Instructions

Create a custom highlight. Three ways: (1) segments = explicit list; (2) start_tick + end_tick (+ pov) for one continuous moment; (3) round_number + player to auto-clip that player's kills in that round. Returns the new highlight (not rendered yet).

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": {
      "match_id": "<match_id>"
    },
    "name": "create_highlight"
  }
}

Input Schema

NameRequiredDescriptionDefault
povNoPlayer to watch.
tagsNo
titleNo
playerNo
end_tickNo
match_idYes
segmentsNo
start_tickNo
descriptionNo
round_numberNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare this is a non-read-only, non-destructive, closed-world operation; the description adds the meaningful post-condition that the returned entity is unrendered, which shapes the caller's next step. It stops short of mutation specifics such as validation of `round_number`/`player`, precedence when several modes are present, or error behavior on out-of-range ticks.

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?

One framing sentence, a numbered enumeration of the three modes, and a single trailing state note. No restatement of the name or filler, and the mode list is front-loaded where the agent needs it.

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?

An output schema exists, so the description correctly avoids detailing the return payload while still flagging the unrendered state. For a 10-parameter creation tool, the remaining gap is mode exclusivity and behavior when no mode parameter is supplied.

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 only 10% across 10 parameters, so the description must carry the load, and it does the highest-value part: it defines which parameters combine to form each of the three modes, including the optional `pov` inside mode 2. It leaves `title`, `description`, `tags`, and the required/optional status of each mode's parameters unexplained, so it does not fully close the coverage gap.

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?

"Create a custom highlight" gives a specific verb and resource immediately, then enumerates three concrete construction modes. An agent can distinguish this from edit_highlight/render_highlight purely from the text.

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?

The description explicitly routes between three mutually exclusive call shapes (explicit `segments`, tick range + `pov`, or `round_number` + `player`), which is real when-to-use guidance at the parameter level. It does not name sibling tools to call afterwards, only hinting via "not rendered yet" that a render step exists, and it never says what happens if multiple modes are supplied.

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