quipu_graph_freeze

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

Annotations only declare destructiveHint/readOnlyHint/openWorldHint; the description goes well beyond them by disclosing that history including retracted rows and transactions is preserved, that the copy is hash-verified before deletion, and that the graph remains addressable at the same IRI. This is exactly the context an agent needs before authorizing an irreversible-looking destructive call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The destructive core (export, verify, delete, re-attach) is front-loaded in one dense sentence and the reading-back and refusal clauses follow logically. It is long but nearly every clause carries operational meaning; only the frozen-dataset URN reference borders on jargon-heavy.

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

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

For a destructive multi-step tool with no output schema, the description covers reversibility, archive location behavior, post-freeze addressability, and refusal cases. Minor gaps remain: no permission/auth requirements for performing a freeze and no statement of what the tool returns on success or on hash-verification failure.

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

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

Schema description coverage is 100%, so graph, timestamp, actor and out_dir are already documented in the schema, including out_dir's default. The description adds no extra semantics about parameter formats or interactions, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource (deep-freeze a named graph) and enumerates the exact mechanics: export full history, hash-verify, delete local rows, re-attach the pack. It is immediately distinguishable from the inverse sibling quipu_graph_thaw and from plain export tools like quipu_export.

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

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

It clearly states the conditions under which the tool refuses to run (ROOT, meta-graph, overlays, attached graphs, double-freeze) and explains how to read the result afterwards via FROM <iri>, the frozen dataset URN, or include_kinds:["archive"]. It never explicitly contrasts with quipu_graph_thaw as the inverse operation, so the when-to-use framing is strong but not fully closed.

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