Skip to main content
Glama

Read a node

hydrate
Read-only

Read one of the owner's nodes by its address (loci://...) or its read-plane url. Not for finding things by a query: search does that, and a hit's address is what hydrate reads.

address takes a loci://<handle>/<path> address or a full read-plane url (https://locihub.link/<handle>/<path>). hydrate reads a url as the owner; a direct GET of one carries no connect token, so it returns only public content. A url returns the body inline; a bare address omits it unless inline=True. Add ?section=<slug> to read one section (see outline). loci://<handle> alone returns the owner's profile; loci://<handle>/.loci the owner's filing rules (YAML, read-only for you) and loci://<handle>/.confirm the latest Confirmed version of each node.

Signed content comes back only after its signature checks out. An address of the caller's own with no confirmed version returns its unsigned text, marked status.signed = false -- a working note, not something the owner stands behind. Another owner's private content is not returned. verify_material=True also returns the node's proof material (envelope, events, key chain, origins), so it can be checked independently.

When present, check (outcome, reasons, certified_seq, signer) says what the stored check found: only confirmed or certified means the owner stands behind this version. Any other outcome (attributed, well-formed, failed), or none, means the owner has not stood behind it.

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": "hydrate"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNo
inlineNo
addressNo
verify_materialNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so safety is covered; the description still adds substantial behavior: signature verification gating, unsigned working notes for the caller's own nodes, exclusion of another owner's private content, and that a bare address omits the body unless inline=True. It stops short of describing error behavior when an address is malformed or unreachable, which keeps it at 4 rather than 5.

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 purpose and the key discriminator before the format details. Three dense paragraphs; almost every sentence adds operative information, though the check-outcome paragraph is long enough to warrant a tighter listing of outcome values.

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?

No output schema, so the description correctly explains what comes back (body inline vs omitted, profile vs .loci vs .confirm, check outcome fields). The main gap is the unexplained 'query' input, which leaves the argument surface partially ambiguous for a 4-parameter tool.

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?

With 0% schema description coverage the description must carry the load, and it does for three of four parameters: address formats (loci:// vs https url, with the connect-token consequence), inline semantics, and what verify_material returns (envelope, events, key chain, origins). The 'query' parameter in the schema is never mentioned and is implicitly discouraged by the sibling hand-off to 'search', leaving one parameter ambiguous.

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?

Opens with a specific verb and resource ('Read one of the owner's nodes') and immediately delimits it against the sibling 'search' for query-based lookup. An agent can distinguish hydrate from search, outline, and list_nodes 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?

Explicitly states when not to use it ('Not for finding things by a query: search does that') and points to the alternative that produces the address hydrate consumes. It also routes section-level reads to 'outline' via the ?section=<slug> hint, and explains how to reach a profile, filing rules, or confirmed versions by address form.

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