llm_fs_analyze_context

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

With no annotations, the description carries full burden. It discloses key behaviors: scans specific files, writes a summary to ~/.llm-router/context_summary.json, and that summary gets injected into system prompts for cheaper models. This adequately covers the tool's side effects and integration.

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 description is front-loaded with the primary purpose, then details the scanned files and output use. It then gives clear usage guidelines and parameters. Every sentence is necessary and no filler. Very concise.

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?

Given the output schema exists, the description need not explain return values. It covers the main function, files to scan, output location, and when to call. It is mostly complete, though it does not mention error handling or missing files scenarios.

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?

The input schema has no descriptions (0% coverage), so the description must compensate. It explains both parameters: path is 'Workspace root to analyze' and max_files is 'Maximum files to read', with defaults listed. This adds sufficient meaning beyond the 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?

The description clearly states the tool's purpose: 'Analyze workspace files to build a routing context summary.' It lists specific files scanned and the output location, distinguishing itself from siblings like llm_analyze and llm_route by explaining that the summary is used by llm_route and llm_auto.

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 provides explicit guidance: 'Call this once at the start of a project session or after major refactors.' It also clarifies that no further action is needed, as the summary is automatically used. However, it does not mention alternative tools or when not to use it.

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