scan_agent_config

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

With no annotations, the description must carry the behavioral disclosure burden. It does convey that the scan is local and limited to listed file types, but it does not state whether the operation is read-only, what it does on detecting injection, or how it treats directories versus files. This is adequate but not thorough.

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 entire description is a single front-loaded sentence with no filler. It packs the action, target file types, scope, and purpose into one concise statement.

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 simple one-parameter tool, the description plus schema covers what to scan and where, but with no output schema the description does not explain what the agent should expect as a result or how findings are reported. Sibling differentiation is also left to inference, leaving minor gaps.

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 the path parameter is already fully documented ('config file or repository root; defaults to the current directory'). The tool description adds no parameter-specific meaning, matching the baseline of 3 for high coverage.

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 uses a specific verb ('Scan'), enumerates the exact resources (AGENTS.md, CLAUDE.md, SKILL.md, .claude, .codex), and states the goal (prompt injection) plus local scope. This clearly differentiates it from sibling tools like scan_prompt_for_injection, which targets arbitrary prompts rather than config files.

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?

The description implies the tool is for scanning local agent/config files for injection, but it does not explicitly state when to prefer it over siblings such as scan_prompt_for_injection, scan_skill_trust, or scan_rag_source. No exclusions or alternative conditions are given.

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