Agentalog — Agent Auto Log

Listing security

listing_security

Read-onlyIdempotent

Read a remote MCP server or SKILL.md review before installing. MCP: server, domain, tools and measured signals. Skill: static findings with file, line, excerpt and context; no command execution or referenced-script review. Unread skills stay unchecked. Read the limits in aviso. Take the id from list_listings. We visit remote MCP servers: initialize and tools/list, without credentials or tool calls, again 7 days after a success. A failure needs a second check. MCP signals: dns_morto, sem_https, tls_invalido, tunel, nao_responde, nao_mcp, texto_suspeito, redireciona_fora, repo_arquivado, repo_parado, dominio_recente, login, bloqueado. For skills, tipo: skill identifies a static SKILL.md review. It flags secret reads, download-and-execute commands, external uploads, invisible characters, long encoded text and broad allowed-tools. revisao.achados supplies the path, original line, excerpt and context. Examples and prohibitions do not raise the level. Excerpts hide sensitive values. The review does not run commands or follow references. Supported source: public raw.githubusercontent.com SKILL.md. Watched, visited, starred and new skills get priority within the shared GitHub governor and a daily cap. Unread or unsupported skills remain explicitly unchecked. Local MCP servers and plugins answer not_remote. No request fetches a third-party source. Cached for 5 minutes.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>"
    },
    "name": "listing_security"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	Listing ID, from `Anuncio.id`.
`api_pass`	No	MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.
`retry_key`	No	Optional retry key, up to 80 ASCII characters; same read for five minutes.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

addedInput schema / properties / api_pass

Added value: +{
+  "description": "MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.",
+  "type": "string"
+}

Changed1 schema field changedOct 15, 2026

removedInput schema / properties / api_pass

Removed value: -{
-  "description": "MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.",
-  "type": "string"
-}

AddedOct 7, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Far exceeds the annotations: it discloses that only `initialize` and `tools/list` are performed, no credentials or tool calls, a re-visit 7 days after success and a second check on failure, a 5-minute cache, shared GitHub governor plus daily cap, and that no request fetches a third-party source. It also states that excerpts redact sensitive values and that commands/references are never followed — exactly the behavioral context a security-review tool needs.

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

Conciseness3/5

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

Purpose is front-loaded, but the body is a dense run-on that repeats itself ('no command execution or referenced-script review' vs 'does not run commands or follow references'; 'Unread skills stay unchecked' appears twice) and buries a long Portuguese signal-name list mid-paragraph. Information is useful but not efficiently organized.

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?

With no output schema and a complex return shape, the description does carry return-value detail: it enumerates the MCP signal vocabulary, defines `tipo: skill`, and names `revisao.achados` fields (path, original line, excerpt, context). Gaps remain on the overall response envelope and how signal severity/levels are reported, despite referencing 'level' changes.

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 only adds that the id comes from list_listings (schema says `Anuncio.id`) and that caching lasts five minutes, which loosely explains retry_key semantics. api_pass and retry_key are not elaborated in the description beyond what the schema already says.

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 a remote MCP server or SKILL.md review before installing,' then splits the two result shapes (MCP: server, domain, tools and measured signals; Skill: static findings with file, line, excerpt). An agent can distinguish this from siblings like get_listing, listing_tools or mcp_index_signals 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 Guidelines4/5

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

Usage context is explicit ('before installing') and it routes ID sourcing to list_listings and limits to 'aviso'. It also states exclusions behaviorally (local MCP servers and plugins answer `not_remote`, unread skills stay unchecked), but it never names a competing sibling tool the agent should pick instead for overlapping needs.

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

All Agentalog — Agent Auto Log tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.