Skip to main content
Glama

Save plain-English descriptions to the codebase graph

graph_describe

Save summaries and change impact notes for pending graph items to .skylos/graph/notes.json. Previous descriptions are kept for comparison, and the graph viewer reads the stored notes.

Instructions

Save descriptions you wrote for items from graph_pending into .skylos/graph/notes.json, where the graph viewer and graph_show read them. A replaced description is kept as the previous one, so readers can see what the code did before. Unknown ids are ignored, and so are impact entries for callers graph_pending did not list with that change. Summaries are capped at 400 characters and impact effects at 300. Writes one local file.

Works without SKYLOS_API_KEY and has no daily limit: it reads the repository on this machine and sends nothing to Skylos Cloud.

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": {
      "items": "<items>"
    },
    "name": "graph_describe"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoProject directory. A relative path resolves against the MCP server's working directory..
itemsYes[{"id": ..., "summary": ...}] for code, or [{"id": ..., "before": ..., "after": ..., "same_behaviour": "yes|no|unclear", "why": ..., "impact": [{"id": "<caller id>", "effect": "<one sentence>"}]}] for changes; ids come from graph_pending, impact ids from that change's callers

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.6.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only give the generic non-read-only/non-destructive/local profile; the description adds real behavior: previous descriptions are preserved, unknown ids and stray impact entries are silently ignored, length caps of 400/300 characters, and a single local file write. It also discloses that no API key or daily quota applies and nothing is sent to the cloud, which matters for an agent deciding whether it can call this freely.

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?

Purpose and destination are front-loaded in the first clause, followed by replacement semantics, tolerance rules, and limits in descending order of importance; the second paragraph cleanly separates the operational/auth facts. No sentence is filler.

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 write tool with two parameters and an output schema, the description covers destination, overwrite semantics, error tolerance, size limits, and auth/quota behavior, leaving nothing an agent needs before calling it.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema: the truncation limits per field and the ignore-unknown-id behavior that determines what the agent should and shouldn't bother sending.

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?

States a specific verb+resource ("Save descriptions... into .skylos/graph/notes.json") and names the upstream source (graph_pending) and downstream readers (graph viewer, graph_show), so the agent can place it in the workflow 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 Guidelines4/5

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

Implies the correct sequencing by requiring items that came from graph_pending and by scoping impact ids to callers that graph_pending listed with that change. It does not spell out an explicit when-not or name a competing write path, but the context is unambiguous.

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