coding_build_codegraph

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

The description adds that the call routes through the platform's domain-agent dispatcher under the JWT, tenant, and company scope, which is helpful context about how the action is executed and authenticated. It does not contradict the annotations, including destructiveHint=true, but it also does not elaborate on what the destructive behavior might be. Since annotations already carry the safety profile, the description adds some but not extensive behavioral detail.

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 short, front-loaded, and has a clear Args list. The routing and scope sentence is useful context and not excessive. It earns its place without being bloated.

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 description covers invocation basics: authentication scope, free-text message, and optional structured inputs. With an output schema and annotations present, the missing return and safety details are less critical. However, the core question of what build_codegraph actually does and when to call it remains unanswered, so the description is only minimally viable for correct tool selection.

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 Args section gives meaning to both schema parameters: message is a free-text objective, and inputs is an optional JSON string of structured inputs. This compensates for the 0% schema description coverage and helps an agent know roughly what to pass. However, it remains vague about what 'structured inputs' should contain or how the message should be phrased.

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 essentially restates the tool name: 'Run the coding domain agent action build_codegraph.' It does not explain what building a codegraph accomplishes, what inputs it expects beyond generic parameters, or how it differs from other coding_* actions. The added routing detail is implementation information, not purpose semantics.

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?

There is no guidance on when to use this tool versus alternatives like coding_get_context, coding_read_code, or coding_chat. The 'free-text objective' hint implies it is an agentic action entry point, but there are no conditions, exclusions, or prerequisites. An agent has to infer the appropriate use case.

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