Skip to main content
Glama

MisakaNet

by org.misakanet
OverviewDiscussionsAdmin

misakanet_search

Read-onlyIdempotent

[RETRIEVAL / READ] Search MisakaNet's public failure-lesson index by error text, keyword, or topic. This is the primary read path — run it first when you hit an error, before deciding to submit anything. For a known lesson ID or path, prefer misakanet_get_lesson — it skips ranking and returns the full content. detail controls progressive disclosure: compact (default, ~80 tok/lesson) for broad scans, summary (~200 tok) adds domain/tags/fix, full returns complete lesson data. FAQ: results may also include answered questions (type="faq", issue_url + answer) — if a maintainer already answered the same question, the answer surfaces here. Returns: object {results: [compact: {id, title, problem, freshness, evidence_level, score} | summary: + {domain, tags, fix} | full: the record], source, detail, query}; score is the ranker's relevance for that result and is omitted on the unranked fallback path. On no match: {no_match: true, suggestion, intake}. When the answer is degraded — no index loaded, or the live store refused the read and the corpus came from the snapshot — the response also carries degraded: true, degraded_reasons and a one-sentence notice; read it before concluding that no lesson exists. Example: misakanet_search(query='pip install timeout', domain='python', top=3)

Input Schema

NameRequiredDescriptionDefault
topNoMaximum ranked results to return. Defaults to 5; keep small for MCP context and latency.
kindNoFilter by kind: 'lessons' (lesson files only), 'evidence' (results with evidence_refs or verification), 'related' (cross-referenced/tag-overlap), 'all' (default). Auto-detected from query intent when omitted.
queryYesRequired redacted error message, keyword, or topic (e.g. 'pip install timeout' or 'DCO sign-off failed').
detailNoProgressive disclosure: compact (default, ~80 tok) includes id/title/problem/freshness/score; summary (~200 tok) adds domain/tags/fix; full returns complete lesson data with path.
domainNoOptional domain filter such as devops, python, network, feishu, rag, fanuc, or mcp.
bm25_weightNoOverride BM25 keyword weight (0-1). Higher favors exact keyword match. Default: 0.65. All weights must sum to 1.0.
baseline_weightNoOverride baseline score weight (0-1). Higher favors proven/popular lessons. Default: 0.15.
metadata_weightNoOverride metadata bonus weight (0-1). Higher favors matching domain/tags. Default: 0.20.

Output Schema

NameRequiredDescriptionDefault
queryNo
detailNo
intakeNo
sourceNo
resultsNo
no_matchNo
suggestionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / detail / description
      Previous value: -"Progressive disclosure: compact (default, ~80 tok) includes id/title/problem/freshness; summary (~200 tok) adds domain/tags/fix; full returns complete lesson data with path."New value: +"Progressive disclosure: compact (default, ~80 tok) includes id/title/problem/freshness/score; summary (~200 tok) adds domain/tags/fix; full returns complete lesson data with path."
  2. Changed1 schema field changed
    • addedInput schema / properties / kind
      Added value: +{
+  "description": "Filter by kind: 'lessons' (lesson files only), 'evidence' (results with evidence_refs or verification), 'related' (cross-referenced/tag-overlap), 'all' (default). Auto-detected from query intent when omitted.",
+  "enum": [
+    "all",
+    "lessons",
+    "evidence",
+    "related"
+  ],
+  "type": "string"
+}
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "detail": {
+      "type": "string"
+    },
+    "intake": {
+      "properties": {
+        "args": {
+          "type": "object"
+        },
+        "tool": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "no_match": {
+      "type": "boolean"
+    },
+    "query": {
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "properties": {
+          "answer": {
+            "type": "string"
+          },
+          "description": {
+            "type": "string"
+          },
+          "domain": {
+            "type": "string"
+          },
+          "id": {
+            "type": "string"
+          },
+          "issue_url": {
+            "type": "string"
+          },
+          "path": {
+            "type": "string"
+          },
+          "score": {
+            "type": "number"
+          },
+          "tags": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "title": {
+            "type": "string"
+          },
+          "type": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "source": {
+      "type": "string"
+    },
+    "suggestion": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  4. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), yet the description adds genuinely non-obvious behavior: the degraded-mode flags (degraded, degraded_reasons, notice) when the index is missing or the live store refused the read, the unranked fallback where `score` is dropped, and the no_match/suggestion/intake shape. That is real value beyond the annotations, though the FAQ aside is narrower in importance.

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 action guidance and following with the alternative and a worked example, so the important routing information comes first. However, the multi-line 'Returns' enumeration is redundant for a tool that already ships an output schema, which is wasted length.

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?

An output schema and full annotations exist, and the description still supplies the pieces those do not: the degraded-answer path, the no-match path, the FAQ result type, and the ranked-vs-unranked score distinction. Nothing an agent needs to interpret a surprising response 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 the baseline is 3. The description's `detail` tiers and token estimates largely restate what the schema already documents (including the compact key list and the weight sum-to-1.0 constraint), so it adds little parameter meaning the agent cannot already read.

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 (Search) plus the exact resource (MisakaNet's public failure-lesson index) and the match dimensions (error text, keyword, topic). It also names the sibling it is not — misakanet_get_lesson — for the known-ID case, so an agent can route without opening a 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 declares itself the primary read path and says to run it first on an error before submitting anything, then carves out the alternative: prefer misakanet_get_lesson for a known lesson ID or path because it skips ranking. That is when-to-use, when-not, and the alternative in one place.

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

All MisakaNet toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources