abstract_dfg

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

With no annotations, the description carries the full burden. It discloses key behaviors: it takes log_id, computes DFG internally, and returns text. A slightly higher score would require mention of side effects or output format, but it is adequate.

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 no wasted words. Key information is front-loaded: the core function first, followed by critical notes on parameters and alternatives.

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 presence of an output schema, return values need not be detailed. However, two of three parameters lack semantic description, and the description does not cover the tool's full scope (e.g., what 'text' format means). It is adequate but incomplete.

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 0%, so the description must compensate. It only explains log_id (and its distinction from dfg_id). The other two parameters (max_len, include_performance) are not described in the description, leaving them semantically undocumented.

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 clearly states the tool produces a text-based directly-follows graph, with explicit distinction from the visual PNG/SVG rendering via the discover_dfg/visualize_dfg pair. It specifies the unique input requirement (log_id not dfg_id).

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?

The description provides explicit guidance on when to use this tool (text output) versus the alternative visual pipeline (discover_dfg + visualize_dfg). It also clarifies that pm4py internally computes the DFG, so no prior discovery step is needed.

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