scan_agent_configs

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

Annotations already declare readOnly, idempotent, and non-destructive, so the description adds real context: it reports whether git tracks a project config (a key in a tracked .mcp.json ships with the repo), orders findings by severity, and flags that transcript scanning is slower and off by default. It stops short of saying what the report contains beyond the agent_files array.

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?

Front-loaded one-line purpose followed by scope, per-parameter notes, and return shape. The client enumeration is long but each item expands coverage meaningfully; no sentence is filler.

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?

An output schema exists, yet the description still names the key return field (agent_files) and its members, and covers all four optional parameters and their defaults. Nothing an agent needs to invoke or interpret this scan correctly is missing.

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 0%, so the description carries the full burden and does: project_path is identified as an optional absolute path, include_user and include_transcripts explain defaults and the cost trade-off, and max_findings specifies 'most severe first' ordering. Every parameter gains meaning absent from the bare schema.

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?

States a specific verb and resource: 'Audit AI agent and MCP client configuration files for hardcoded secrets'. The scope (client configs plus agent instruction files, project and user level) clearly separates it from siblings like scan_file, scan_directory, and scan_text.

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?

Gives clear context on the files it targets (`.mcp.json`, `.claude/settings*.json`, `.cursorrules`, user-level configs for named clients) and the defaults that shape a run (include_user=true, include_transcripts=false and 'slower'). It never states explicit exclusions or names a sibling alternative such as scan_directory, so routing is implied rather than spelled out.

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