Tirith

Official

Overview Schema Source Related Servers Discussions Admin

memory_delete

DestructiveIdempotent

Permanently remove a memory note by permalink, id, or exact title to retract secrets or wrong facts. Correct notes with memory_write instead.

Instructions

Delete one memory note by permalink, id or exact title, permanently: its file is removed and does not return on restart. Use to retract a note that holds a secret or a wrong fact; to correct a note use memory_write, which updates in place. Lead-only while a swarm has a lead. Returns a digest of what was removed; not_found if there is none.

Input Schema

Name	Required	Description	Default
`name`	Yes	A permalink, an id, or an exact title.
`agent`	Yes	Your stable agent name.

Output Schema

Name	Required	Description
`lead`	No	On a lead-only conflict: the lead to message.
`status`	Yes	ok. conflict: lead-only while a swarm has a lead. not_found: no such note.
`message`	No	Human-readable detail, on most outcomes other than ok.
`removed`	No	A digest of the deleted note: permalink, title, kind, paths, tags, updated_at, and a 160-character excerpt.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.3.0Oct 16, 2026

addedOutput schema / properties / lead

Added value: +{
+  "description": "On a lead-only conflict: the lead to message."
+}

changedOutput schema / properties / status / description

Previous value: -"ok. not_found: no such note."New value: +"ok. conflict: lead-only while a swarm has a lead. not_found: no such note."

Changed3 schema fields changedv1.1.2Sep 18, 2026

addedInput schema / properties / agent / description
```
Added value: +"Your stable agent name."
```

addedInput schema / properties / name / description

Added value: +"A permalink, an id, or an exact title."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "description": "Any result may also carry lost, inbox, inbox_more and persist_error; see guide.",
+  "properties": {
+    "message": {
+      "description": "Human-readable detail, on most outcomes other than ok.",
+      "type": "string"
+    },
+    "removed": {
+      "description": "A digest of the deleted note: permalink, title, kind, paths, tags, updated_at, and a 160-character excerpt.",
+      "type": "object"
+    },
+    "status": {
+      "description": "ok. not_found: no such note.",
+      "enum": [
+        "ok",
+        "conflict",
+        "not_found",
+        "none",
+        "invalid",
+        "cancelled"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "status"
+  ],
+  "type": "object"
+}

First observedv1.1.1Sep 18, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only declare destructiveHint and idempotentHint; the description adds substantive traits beyond them — the file is physically removed, it does not return on restart, a lead is required during a swarm, and the return is a digest or not_found. This is exactly the extra context annotations cannot carry.

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?

Three tight sentences: effect first, then the use/alternative, then permission and return. Zero filler and the critical destructive semantics are front-loaded.

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 destructive two-parameter tool, the description covers the mutation, reversibility (permanent, file removed), authorization gating, the sibling alternative, and the failure mode. The output schema covers return shape, so nothing an agent needs to invoke it correctly is missing.

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 100%, so both parameters are already documented in the schema. The description restates the accepted identifier forms but adds no format, ordering, or disambiguation guidance beyond the schema, so the baseline 3 applies.

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 and resource ('Delete one memory note'), the accepted identifiers (permalink, id, exact title), and the permanence of the effect. It is clearly distinguished from memory_write, which the description explicitly routes correction work to.

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?

Gives explicit when-to-use ('retract a note that holds a secret or a wrong fact'), names the alternative ('to correct a note use memory_write, which updates in place'), and states a gating condition ('Lead-only while a swarm has a lead'). Nothing is left to inference.

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