compare_graph_to_scip

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

With no annotations, the description carries the full burden. It discloses that the tool requires a prior command, reports nothing under certain conditions, and outputs disagreement edges. It does not mention auth or side effects, but as a diagnostic tool, mutation is unlikely. This is adequate for a read-only diagnostic.

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 sentences, with the core action in the first sentence. Every clause adds value: cross-check action, output type, tool purpose, prerequisite, and edge case behavior. No wasted words.

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 no output schema, the description explains what the tool returns (edges of disagreement) and a key edge case (no oracle data). It doesn't detail the format of the report, but for a simple diagnostic, this is sufficient. The complexity is low (no parameters).

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?

There are no parameters (schema coverage 100% with empty schema). The description does not need to add parameter information. Baseline for 0 parameters is 4, 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 uses a specific verb 'Cross-check' and clearly identifies the resources: 'tree-sitter graph' and 'SCIP compiler oracle'. It explicitly states the output: 'report the edges where they DISAGREE on a callee's resolution'. This uniquely defines the tool's purpose and differentiates it from siblings like compare_graph_to_text.

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 the prerequisite 'requires `rag-rat oracle run` first' and the condition 'reports nothing when no oracle data exists'. It also labels it as a 'resolver-debugging diagnostic', indicating the use case. However, it does not explicitly contrast with siblings or provide when-not-to-use guidance, though the context implies its niche.

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