Skip to main content
Glama

Draw other angles of a place

draw_place_angles

The same set from three-quarter, side or low, each a new place (spends credits) A place only. Without confirm: the price (credits per angle and the total), nothing drawn; tell the user, then send confirm true after their go (and credits: the total shown; a different price answers 409 with the current quote). Each angle is one picture of the same place, its layout, props, colours and light, from another side, empty of people, drawn in about a minute; it comes back as a new place in the same artist's kit (owned and shared like the place), named " · side", with angle_of (the first place of its set) and angle. A new angle is pending: the user keeps it (update_kit_piece with kept true) or leaves it out (delete_kit_piece); a brief can mention it once kept. A brief that mentions places of one set gets them as one set: the director cuts between the angles. Credits are held, then charged for each picture drawn (failed lists any that couldn't be, not charged). Needs an active plan (402 plan_required without one; get_account: plan.active) and room in its storage (402 storage_full when it would not fit; get_account: storage).

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": {
      "kit_id": "<kit_id>"
    },
    "name": "draw_place_angles"
  }
}

Input Schema

NameRequiredDescriptionDefault
anglesNoWhich sides: three-quarter, side, low (default: all three)
kit_idYesThe place (kit piece) id
confirmNotrue: draw them (spends credits); left out: only the price
creditsNoWith confirm: the total price shown, so a changed price is refused

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, non-idempotent, open-world), it discloses credit hold-then-charge semantics, which failures are not charged, an approximate one-minute draw time, that the output lands as a new place in the same artist's kit with angle_of/angle metadata, and the pending-approval state. It also names the exact gating conditions and error codes: 402 plan_required and 402 storage_full, with get_account pointers for checking.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Nearly every clause carries information, and the spending/purpose statement is front-loaded, but the text is one dense run-on block with fragments ('A place only.') and convoluted phrasing like 'send confirm true after their go'. Splitting the draw flow, the pending-result handling, and the preconditions into distinct sentences would markedly improve scanability.

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 credit-spending, multi-output generative write with no output schema, the description covers preconditions, cost model, confirmation safety, artifact naming and metadata, downstream approval, and failure accounting. An agent has everything needed to call it safely and interpret the outcome.

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 already 100%, so the baseline is 3; the description adds real meaning on top, notably that credits is a price-matching guard whose mismatch returns 409 with the current quote, and that omitting confirm yields a quote with nothing drawn. The angles default (all three) is duplicated from the schema rather than extended.

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 states a specific verb and resource plus the exact variants produced: 'The same set from three-quarter, side or low, each a new place (spends credits)'. The scoping line 'A place only' immediately distinguishes it from the sibling drawing tools (character sheet, music video cast/frame), so an agent can route correctly without opening a schema.

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 an explicit two-step protocol with an alternative outcome: omit confirm to get only the price and tell the user, then send confirm true with the total after approval, noting a changed price answers 409. It also names follow-up tools for the pending result (update_kit_piece with kept true, or delete_kit_piece), covering when to use each instead of this one.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources