get_supervision_tree

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

With no annotations provided, the description carries the burden of transparency. It discloses the recursive behavior ('Recursively walks supervisors'), the output content ('PIDs, types, and child counts'), and the prerequisite ('You MUST specify the app name'). While it does not explicitly state that the operation is read-only or describe error handling, the getter nature is implied and the behavioral description is informative enough for an agent to infer the tool's impact. This earns a 4.

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 well-structured sentences: the first states core purpose with output detail, the second gives a prerequisite and a fallback discovery method. It is front-loaded, every sentence serves a distinct function, and there is no redundant or filler content. Perfectly concise for the tool's complexity.

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 tool's simplicity, the description covers the essential context: what it returns (hierarchy with PIDs, types, child counts), the required input (app name), and a way to resolve the input if unknown. It does not mention behavior for unknown apps or when depth might be insufficient, but this is a minor omission for a getter tool. The output schema is absent, so the description's return-value hints are useful and adequate.

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%, with both parameters already described in the schema. The description adds value by emphasizing the app parameter's mandatory nature ('You MUST specify the app name') and providing guidance on how to find valid app names, which goes beyond the schema's field descriptions. It also reinforces the depth parameter indirectly through the demonstrated recursive behavior. This exceeds the baseline of 3.

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's purpose: 'Get the OTP supervision tree for an application.' It specifies the verb ('Get'), the resource ('OTP supervision tree'), and the scope ('for an application'), and goes further to describe what it does ('Recursively walks supervisors showing the full hierarchy of processes with PIDs, types, and child counts'). This distinguishes it from sibling tools like list_processes or get_process_info, which focus on individual processes rather than the hierarchical tree.

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 clear usage context: 'You MUST specify the app name' and gives a fallback approach for finding valid app names ('Use get_app_config or project_eval with Application.started_applications() to find app names if unsure'). This tells the agent when and how to use the tool, but it does not explicitly state when not to use it or name alternative tools for different scenarios. It's a minor gap, so a 4 is appropriate.

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