graph_explore

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

With no annotations, the description carries the full burden. It discloses the core behavior: finds entities related to the query, then traverses callers, callees, imports, and inheritance up to `depth` hops. This goes beyond the title and gives the agent a clear model of what happens. It stops short of stating whether the operation is strictly read-only or how results are returned, but the exploratory nature is well conveyed.

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 two tight sentences. The first front-loads the use case with concrete examples, and the second states the traversal behavior while naming the alternative tool. Every clause adds value, with no filler or redundancy.

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?

The tool has 10 parameters, no description coverage in the schema, no annotations, and no output schema. The description covers when to use it and the core traversal idea, but it omits the meaning of most parameters, return format, and any caveats or prerequisites. For a tool of this complexity, this is a material gap.

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 must compensate for all 10 parameters, but it only explains `depth` ('up to depth hops'). Parameters like `use_hyde`, `use_hybrid`, `rerank_pool`, `use_graph_scoring`, and `use_summary_vector` are left entirely to name inference, which is insufficient for a tool with this many tuning knobs.

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 ('explore', 'traverses') and resource (graph/connections) and clearly states the tool provides a structural/architectural view rather than code snippets. It explicitly distinguishes itself from `search_code`, and the examples ('what depends on X', 'call graph around Y') make the purpose 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 gives explicit when-to-use guidance: when the user wants dependency/call-graph/architecture insight. It also provides an explicit exclusion and alternative: for 'find the code that does X', use `search_code` instead. This leaves little ambiguity about tool selection.

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