Tirith

Official

by eabz

Overview Schema Source Related Servers Discussions Admin

Rust

Local

memory_search

Read-only

Find memory notes by free text, path, kind, tag, or time, best match first; omit query to list recently updated notes.

Instructions

Find memory notes by free text, path, kind, tag or time, best match first; with no query it lists the most recently updated, which is the call to make when a session starts. Rows are digests with a 160-character excerpt and a score, never bodies: read one with memory_read. Terms match as substrings, with no embeddings. truncated is true when limit hid matches.

Input Schema

TableJSON Schema

Name	Required	Description
`tag`	No	Only notes carrying this tag.
`kind`	No	Only notes of this kind.
`path`	No	Only notes whose paths overlap this one.
`agent`	Yes	Your stable agent name.
`limit`	No	How many to return. Default 10, max 50.
`query`	No	Free text. Omit for recent activity.
`since`	No	Only notes updated at or after this RFC 3339 timestamp.

Output Schema

TableJSON Schema

Name	Required	Description
`count`	No	Rows in this response.
`notes`	No	Best match first, or newest first with no query. Digests, never bodies: permalink, title, kind, paths, tags, updated_at, and a 160-character excerpt, and score.
`status`	Yes	ok. invalid: bad kind, since, or input.
`message`	No	Human-readable detail, on most outcomes other than ok.
`truncated`	No	True when limit hid further matches.

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv1.1.2Sep 18, 2026

addedInput schema / properties / agent / description
```
Added value: +"Your stable agent name."
```
addedInput schema / properties / kind / description
```
Added value: +"Only notes of this kind."
```

addedInput schema / properties / kind / enum

Added value: +[
+  "fact",
+  "lesson",
+  "gotcha",
+  "handoff",
+  "research",
+  "decision",
+  "note"
+]

addedInput schema / properties / limit / description

Added value: +"How many to return. Default 10, max 50."

addedInput schema / properties / path / description

Added value: +"Only notes whose paths overlap this one."

addedInput schema / properties / query / description

Added value: +"Free text. Omit for recent activity."

addedInput schema / properties / since / description

Added value: +"Only notes updated at or after this RFC 3339 timestamp."

addedInput schema / properties / tag / description
```
Added value: +"Only notes carrying this tag."
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "description": "Any result may also carry lost, inbox, inbox_more and persist_error; see guide.",
+  "properties": {
+    "count": {
+      "description": "Rows in this response.",
+      "type": "integer"
+    },
+    "message": {
+      "description": "Human-readable detail, on most outcomes other than ok.",
+      "type": "string"
+    },
+    "notes": {
+      "description": "Best match first, or newest first with no query. Digests, never bodies: permalink, title, kind, paths, tags, updated_at, and a 160-character excerpt, and score.",
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "status": {
+      "description": "ok. invalid: bad kind, since, or input.",
+      "enum": [
+        "ok",
+        "conflict",
+        "not_found",
+        "none",
+        "invalid",
+        "cancelled"
+      ],
+      "type": "string"
+    },
+    "truncated": {
+      "description": "True when limit hid further matches.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "status"
+  ],
+  "type": "object"
+}

First observedv1.1.1Sep 18, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Even with readOnlyHint=true, the description adds substantial behavioral detail: rows are digests with a 160-character excerpt and a score, terms match as substrings with no embeddings, and truncated=true signals hidden matches. This tells the agent what to expect without relying on structured fields alone.

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?

The description is three sentences and every sentence earns its place: purpose, usage trigger and body-read alternative, then matching and truncation behavior. No filler or redundancy.

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 read-only search tool with full parameter documentation and an output schema, the description is complete. It covers result format, sorting, matching behavior, truncation, and the session-start use case.

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 semantics beyond the schema by explaining that an omitted query means recent activity and that terms match as substrings. It also defines the truncated flag's meaning in relation to limit.

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?

The description opens with a specific verb and resource ('Find memory notes') and enumerates the search dimensions: free text, path, kind, tag, and time. It distinguishes itself from memory_read by clarifying that search returns digests, not bodies.

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?

It gives an explicit trigger: with no query, list recent notes, which is 'the call to make when a session starts.' It also names the alternative memory_read for retrieving full bodies, giving the agent clear routing guidance.

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