Get Table Dependencies

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, and the description adds substantial behavioral detail: what executable, datatype, and vocabulary nodes contain; how dispatchers, self-loops, cycles, and inheritance are represented; how truncation and previews appear; and how JSON vs Markdown variants render. There is no contradiction with the 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?

The description is long but densely informative, moving from core behavior to mode selection to output rendering. Every sentence adds distinct value, including the Mermaid rendering details that matter for choosing response_format. There is no tautology or filler.

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?

For a tool with no output schema, the description covers the response semantics surprisingly well: it defines the adjacency-list graph, the node types, the meaning of dispatchers, self-loops, and cycles, and the differences between JSON and the Markdown variants. Required projectId and parameter constraints are already covered by the schema, so nothing essential is missing.

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 100%, so the baseline is a 3. The description adds conditional meaning beyond the schema, such as 'omit tableId for the whole project graph' vs 'provide tableId for its dependency/dependent neighborhood,' and explains how response_format affects the output. It does not independently document every parameter, but it meaningfully supplements the schema.

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 a specific verb and resource: 'Get the table dependency graph as an adjacency list.' It then clearly distinguishes the two main call modes: whole project/module graph when tableId is omitted, and dependency/dependent neighborhood when tableId is provided. This makes the tool's purpose immediately distinguishable from sibling table tools like openl_get_table or openl_list_tables.

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 explicitly explains when to omit or provide tableId, when to use direction and depth, and how module and layer restrict the graph. It even points to openl_list_project_modules() for discovering module names. It stops short of explicitly naming sibling tools to avoid or saying 'use this instead of X,' so it is just below a 5.

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