get_system_dependencies

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

The description explicitly notes 'Read-only; no side effects' and explains the satisfaction criteria in detail, going beyond the tool name. It does not mention error handling or permission requirements, but for a read-only query this is a reasonable level of transparency given no annotations.

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?

Four sentences, front-loaded with the core purpose, then a brief return explanation and usage guidance. Every sentence adds value without unnecessary verbosity.

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 purpose, return semantics, and usage, but leaves server_version unexplained. Since an output schema exists, return structure is not a gap; however, the undocumented required parameter represents a completeness hole in an otherwise solid description.

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 description provides no parameter-specific details. The schema covers only system_id with a one-line description, while server_version is entirely undocumented. With only 50% schema coverage and no description compensation, the agent has insufficient understanding of server_version.

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 'Get the cross-model dependency graph for a system,' a specific verb+resource statement. It further clarifies the graph consists of cross-model dependencies with satisfaction status, distinguishing it from other system-level read tools like get_system or get_composition_overview.

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 explicitly states 'Use to see which assumptions are met by other models' controls, find unsatisfied dependencies, or check system-level completeness.' It also points to link_dependency as the counterpart for creating these links, providing clear guidance on when to invoke this tool.

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