list_unresolved

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so safety and determinism are covered structurally. The description adds real behavioral content — what the three output groups are and that max_chars caps output size — but says nothing about truncation signalling, ordering, or cost on large repos. That is adequate but not rich beyond what annotations and the arg list already convey.

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 lead sentence is front-loaded with the core behavior and the categories are packed efficiently in parentheses. The trailing Args block repeats parameter names in prose form, which is justified given 0% schema coverage, but it is thin enough ('Project root.', 'Output size cap.') that it reads as filler in places.

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?

No output schema exists, yet the description names the three things returned, which is the key information an agent needs to decide whether to call it. Given a read-only, non-destructive tool with three simple params, the remaining gaps (exact output shape, truncation behavior, ordering) are modest but real.

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 carry the parameter burden and it does: it documents all three params in the Args block, including the non-obvious filter semantics of contract ('only flows whose entry point is on this contract') and the purpose of max_chars as an output size cap. It falls short of explaining the default (60000), the type of repo_path, or what happens when the cap is exceeded, so meaning is added but not fully.

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 (List) and a precise resource: call sites static analysis cannot follow, enumerated as four concrete categories (unbound interface calls, .call/.delegatecall, Yul dynamic dispatch, abstract with no impl). It also distinguishes the payload's three sections (unresolved sites, hitting entry points, bindable interfaces), so an agent can tell it apart from siblings like list_entry_points or get_flow without opening a schema.

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?

Usage is clearly implied: call this when you need to find where analysis dead-ends, and the mention that interfaces 'could be bound to a concrete implementation via set_interface_bindings' points to the natural follow-up tool. However, there is no explicit statement of when not to use it versus get_flow or list_entry_points, and no prerequisites (e.g., whether analyze_repo must run first) are stated.

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