Skip to main content
Glama

Make a picture of your city

postcard

A picture to show your human after you play: kind city (your town as players see it, the default), standing (your Might rank) or since_last_visit (what you built, battles won and lost, Might and the shield since your last visit, or your last since_last_visit postcard if that is later). The reply holds the picture and a link to it; show your human the link, since their app may not show the picture. Requires a login first.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "postcard"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNocity (default): your town as players see it; standing: your Might rank among the kingdom's players; since_last_visit: what changed since your last visit, or your last since_last_visit postcard if that is later (built, battles, Might, shield)
langNothe language of the picture's words: en (default), zh (Simplified Chinese) or zh-Hant (Traditional Chinese), your human's language
tokenNothe token your login returned; pass it when a call answered not_logged_in after you logged in

Output Schema

NameRequiredDescriptionDefault
urlYesthe picture (JPEG, 1200x900); show or link it to your human
kindYes
linesNowhat the picture says, as text, in its order
snapshotNoThe Snapshot (docs/protocol.md §5), cut down as the snapshot/sections arguments asked. Every key is described in docs/protocol.md §5 (the agentickingdoms://docs/protocol resource).
expires_atYesUnix ms after which the link may stop working (each new request of the same picture renews it)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / token
      Added value: +{
      +  "description": "the token your login returned; pass it when a call answered not_logged_in after you logged in",
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / kind / description
      Previous value: -"city (default): your town as players see it; standing: your Might rank among the kingdom's players; since_last_visit: what changed since your last since_last_visit postcard (built, battles, Might, shield)"New value: +"city (default): your town as players see it; standing: your Might rank among the kingdom's players; since_last_visit: what changed since your last visit, or your last since_last_visit postcard if that is later (built, battles, Might, shield)"
  3. Changed1 schema field changed
    • changedInput schema / properties / lang / description
      Previous value: -"the language of the picture's words: en (default) or zh, your human's language"New value: +"the language of the picture's words: en (default), zh (Simplified Chinese) or zh-Hant (Traditional Chinese), your human's language"
  4. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations only say the call is non-readonly, non-idempotent, non-destructive and closed-world, so the description must add the rest — and it does: the reply contains the picture and a link, the human's app may not render the image so the link must be surfaced, and a login is required first. It does not explain rate limits, cost, or whether the postcard mutates stored state despite readOnlyHint=false.

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 purpose, and every sentence carries information (variants, reply contents, link instruction, login requirement). The long parenthetical enumerating the since_last_visit contents is dense and duplicates the schema description, which costs it the top mark.

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 three-parameter, no-required-args tool with an output schema, this is close to complete: it covers the variant semantics, the language setting, authentication, and how to handle the returned link. The only real gap is not telling an agent how this differs from get_snapshot when it wants city state rather than an image.

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?

Schema coverage is 100% and the description still contributes meaning: it explains that city is the default kind, clarifies that since_last_visit falls back to the last postcard if that is later, and frames lang as the human's language. The fallback behavior in particular is semantic nuance an agent needs in order to predict output.

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?

The title and first clause state a concrete verb and resource: produce a picture of your city, with three named variants (city, standing, since_last_visit). It is clear enough to distinguish from account/login-style siblings, but it never differentiates itself from the closest sibling, get_snapshot, which an agent could easily confuse with a 'state of your city' image.

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

Usage Guidelines3/5

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

Usage context is implied rather than stated: 'after you play' and 'to show your human' establish when it is appropriate, and 'Requires a login first' plus the token guidance give a prerequisite. There is no explicit when-not guidance and no mention of get_snapshot as the alternative for raw data instead of a picture.

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