build_graph

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

With no annotations provided, the description carries full burden. It thoroughly discloses caching behavior (content-addressed, instant for unchanged trees), refresh semantics, loading of the graph on success, toolchain prerequisites (node, clang) with actionable errors, and performance caveats (in-process, can take minutes, timeout). This is exceptionally transparent.

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 well-structured and front-loaded: purpose first, then caching, loading, toolchain, and performance. Each sentence adds value with no fluff, though it is somewhat lengthy at ~150 words. Overall effective and easy to scan.

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?

Covers purpose, usage context, prerequisites, caching, performance, and timeout. Missing explicit description of the return value/content (since no output schema exists), but the side effect of loading the graph for subsequent calls is described. Slight gap on what text/json output contains, but overall complete for the tool's primary function.

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 coverage is 100%, so each parameter is already documented in the schema. The description adds context on timeout semantics (can take minutes, default 300) and refresh meaning, but doesn't introduce significant new meaning beyond the schema. Baseline 3 is appropriate given high schema 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 states a specific verb (build) and resource (Lachesis graph from source directory), and clearly differentiates from siblings by calling it the zero-config way to start on a repo with no graph yet, with no separate build step needed. This distinguishes it from load_graph and other analysis tools.

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?

Provides explicit context: use when starting on a repo with no graph yet, and includes guidance on handling long builds (smaller subtree or out-of-band lachesis build). While it doesn't name alternatives like load_graph directly, the use case is clear enough for an agent to select the right tool.

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