invariant_trace

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

With no annotations provided, the description carries the full burden and discharges it well: it declares 'Read-only' up front, which is the key safety behavior. It also discloses the return shape (role-tagged nodes with file:line) and the bounded nature by `depth`. It does not discuss failure modes or performance, but for a read-only analysis tool the essential behaviors are covered.

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, each earning its place: the first defines the operation, the second gives the use case and return format, the third draws the boundary against alternatives. The 'Read-only' safety cue is front-loaded, and there is zero fluff or repetition.

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 tool's moderate complexity and the absence of an output schema, the description provides enough to call it correctly: it explains the return structure, the local scope, and how to choose a different tool. The only minor gap is that `format`'s text vs json behavior is not explicitly referenced in the description, though the schema covers it.

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 the baseline applies. The description does add a small semantic link by saying results are 'bounded by `depth`', but this largely echoes the schema's own 'how many flow hops' wording. It adds no meaning for `value`, `limit`, or `format` beyond what the schema already states.

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 opens with the specific verb 'Trace' and clearly defines the resource: producers, mutators, checkers, and consumers of a value or field over a bounded local flow cone. It explicitly distinguishes itself from interprocedural siblings like `flow` and `sources_of` by stating 'Local, not interprocedural', leaving no ambiguity about its scope.

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 states when to use the tool ('Use it to reconstruct an invariant around one value') and explicitly routes the agent to alternatives when the task crosses call seams ('use `flow` / `sources_of` to cross call seams'). This is direct, actionable guidance that prevents mis-selection among the many sibling tools.

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