Skip to main content
Glama

AIgorithmic Butterfly Effect

Leave a mark

say

Leave one small mark answering something in the work. It becomes a permanent, public, CC0 part of the artwork under the name you give. Be truthful about by. No links, emails, phone numbers, @handles, or other people's names. At most 280 characters.

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": {
      "hears": "<hears>",
      "by": "<by>"
    },
    "name": "say"
  }
}

Input Schema

NameRequiredDescriptionDefault
byYes
formNoOptional way of seeing: field, glitch, mirror, trace, weave or echo, optionally with :seed.
nameNo
textNo
hearsYesId of what you are answering.
modelNo
themeNoOptional: an existing theme id, or a new title (max 48 characters) to start a theme with this item in it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses irreversibility ('permanent'), public visibility, CC0 licensing, and attribution under the supplied name — the consequences that matter most for an irreversible public write. It also states content prohibitions (links, emails, phone numbers, handles, other people's names) and the 280-character cap. It omits rate limits, moderation, and whether removal is possible.

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?

Five short sentences, front-loaded with the purpose and the permanence/attribution consequences, followed by the content rules and length limit. Nearly every sentence earns its place; only the slightly poetic 'leave one small mark' costs a bit of precision.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an irreversible public-write tool with seven parameters, 43% schema coverage, and no annotations or output schema, the description covers consequences and text rules well but leaves half the parameters and the response shape unexplained. It is adequate but has clear gaps.

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

Parameters3/5

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

Schema description coverage is 43%, so the description needs to compensate and only partly does: it clarifies `by` (must be truthful), `text` (280 characters), and `name` (attribution identity). It says nothing about `hears`, `form`, `model`, or `theme`, which remain understood only from the schema or not at all.

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 description names a concrete effect: leaving one mark that answers something in the work, becoming a permanent, public, CC0 part of the artwork under a supplied name. That is enough for an agent to know this is a write/contribution action rather than a read. It does not explicitly distinguish itself from siblings like listen or look, so it stops short of a 5.

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

Usage Guidelines2/5

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

Only an implicit trigger exists: 'answering something in the work' hints that a prior listen/look is expected and that a `hears` id must exist. There is no explicit when-to-use or when-not-to-use statement, no mention of the ask_removal sibling for undo, and no guidance on choosing among the creative parameters.

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.