refresh_graph

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

With no annotations, the description carries the full burden, and it delivers. It explains the incremental vs. full re-parse behavior, mentions mirror re-syncing on Windows-mount projects, performance (~seconds), and the automatic file watcher behavior. This is rich behavioral context beyond what any annotation would provide.

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?

Three sentences, front-loaded with the core purpose, then usage, then behavior. Every sentence earns its place, and there is no redundant or generic 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?

Despite having no parameters and no annotations, the description fully covers the operation, usage scenarios, behavioral nuances (incremental vs. full parse), platform-specific behavior, and the fallback to the file watcher. An output schema exists, so return values do not need explanation. This is complete for the tool's complexity.

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 tool has zero parameters, so there is nothing to document. The baseline for 0-parameter tools is 4, and the description adds helpful context about when the tool applies, which is appropriate.

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 function: 'Bring the codebase graph up to date with the code on disk.' This is a specific verb+resource pairing that distinguishes it from the sibling tools, which are all read/query operations (e.g., get_file_context, get_dependency_graph). The purpose is unmistakable.

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?

It explicitly says 'Use this after making changes to the codebase, or if the graph seems stale.' It also provides an important usage caveat: 'Normally the file watcher handles this automatically on native projects,' which tells the agent when this tool may be unnecessary. This is strong when-to-use guidance.

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