reason_graph

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

With no annotations provided, the description carries the full burden. It discloses the key behavioral trait that session carries state across rounds, which is valuable. However, it does not mention whether the tool is read-only, what it returns, or any side effects, leaving notable gaps in behavioral transparency.

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 concise, using a compact arrow notation to summarize the reasoning flow and a separate sentence for session state. Every word earns its place, making it efficient and front-loaded, though the notation might be slightly cryptic for some readers.

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 is complex with a nested step object and multiple action types, yet the description provides only a high-level protocol overview. It lacks operational details such as how to start a session, how to chain steps, expected return values, and error handling. Given no output schema, the description is insufficient for reliable multi-round use.

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?

The schema covers 75% of parameters with descriptions, including a detailed explanation of the step object. The description adds context about the protocol flow and the role of session in carrying state, which helps clarify parameter usage. However, it does not provide significant per-parameter details beyond what the schema already offers.

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 is an interactive graphical reasoning protocol with a multi-round loop from primitives (locate/measure) to semantics (semantic/hypothesis) to annotation (annotate/verify). This distinguishes it from single-step sibling tools like ocr_image or locate_object, though the term 'reasoning protocol' is somewhat abstract.

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 implies use for multi-round iterative reasoning tasks on images, mentioning the loop and session state. However, it does not explicitly state when to use this tool versus simpler alternatives, nor does it provide any exclusions or when-not-to-use guidance.

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