Skip to main content
Glama

Sato Hub: Build Onchain & Crypto Agents

by ai.satohub
OverviewDiscussionsAdmin

Sync a copy of the directory

onchain_agent_get_changes
Read-onlyIdempotent

USE WHEN you keep a local copy of the directory and need only what moved since your last sync (machine-readable added / updated / removed), rather than re-fetching the whole catalog. NOT FOR a readable headline feed or one project's history (use onchain_agent_recent_changes instead), or the current state of one record (use onchain_agent_get_resource).

RETURNS (json): what changed since a given date: additions, per-resource change events, and retirements. { since, until, window_days, next_since, counts:{added,changed,removed}, added:[...], changed:[{slug,name,url,events:[...]}], removed:[...], coverage:{...}, full_export }.

CURSOR: next_since is the date to pass as since on your next call. It starts the next window at a snapshot taken before this read, so a change cannot fall between two calls; it overlaps by a couple of days, so dedupe by slug. To watch a fixed list of listings, call on a schedule with since = the last next_since and look for your slugs in each lane. A call with no argument returns a truncated sample: take the cursor from a call with since or detail "full", not from the sample.

COVERAGE (also stated in the response): added is exact. updated is a field-level diff of every catalog field between the snapshot on baseline_date and the live record — complete at daily resolution, so a quiet copy edit IS caught. changed is the richer event log (score moves, releases, verification) and explains WHY. removed is approximate. Mirror from added + updated + removed. Read-only.

WITH NO since (and no detail: "full") the answer is compact, labelled rule "defaulted": exact counts for the default 14-day window and the newest rows of each lane (summary: true, shown, omitted, order, example_calls). It is a sample, not a sync. Pass since (any date) or detail: "full" for every row; a later since is a shorter window and a smaller answer. All free.

Examples:

  • "what moved recently" -> {} (compact) · every row -> { detail: "full" }

  • "what's new this week" -> { since: "2026-08-23" }

  • "sync my copy" or "watch my list" -> { since: }

Input Schema

NameRequiredDescriptionDefault
sinceNoReturn everything that changed since this ISO date. Defaults to 14 days ago. Clamped to the 90-day supported window.
detailNo'full' returns the whole feed for the default 14-day window even with no `since`. Omitted with no `since`, the answer is compact: exact counts for the window plus the newest rows of each lane, and the exact calls for the rest.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / detail
      Added value: +{
+  "description": "'full' returns the whole feed for the default 14-day window even with no `since`. Omitted with no `since`, the answer is compact: exact counts for the window plus the newest rows of each lane, and the exact calls for the rest.",
+  "enum": [
+    "summary",
+    "full"
+  ],
+  "type": "string"
+}
  2. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover read-only/idempotent safety, but the description goes far beyond: cursor semantics (next_since starts the window at a pre-read snapshot so nothing falls between calls, with a couple of days of overlap requiring dedupe by slug), per-lane accuracy (added exact, updated field-level diff, removed approximate), and the trap that a no-argument call is a truncated sample, not a sync. It also states 'Read-only', consistent with readOnlyHint.

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 decision rule and clearly sectioned (USE WHEN / NOT FOR / RETURNS / CURSOR / COVERAGE / examples). Dense but nearly every sentence carries actionable information; the COVERAGE paragraph is the heaviest and could be tightened slightly.

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?

With no output schema, the description carries the return burden fully — it enumerates the response shape, counts, lanes, coverage, and full_export — and additionally explains the non-obvious default behavior and the sync contract. Nothing an agent needs to call this correctly is missing.

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 baseline is 3, but the description adds real usage meaning beyond the schema: feed `since` from your previous `next_since`, a later `since` yields a shorter window and smaller answer, and `detail: "full"` overrides the compact default. Only the 90-day clamp detail is essentially restated from the schema.

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 operation (delta retrieval against a local copy) and its scope (added / updated / removed since last sync), and explicitly carves itself away from onchain_agent_recent_changes and onchain_agent_get_resource. An agent can pick it correctly without opening any 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?

Explicit USE WHEN / NOT FOR blocks name the two competing siblings and the conditions that select them, and the examples map natural-language requests ('sync my copy', 'what moved recently') to concrete argument choices. Exclusion guidance is unambiguous.

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

All Sato Hub: Build Onchain & Crypto Agents toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources