node_errors_deep

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

With no annotations provided, the description carries the full burden and does a good job: it discloses that only nodes with problems are returned, explains the three detail modes, and mentions that YAML is the token-cheap default. It stops short of stating side-effect safety explicitly, but 'walk and report' strongly implies a read-only operation.

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 opening sentence establishes the core behavior immediately, and the parameter list is compact and scannable. Every line adds necessary information, and there is no filler or repetition.

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 read-oriented traversal tool with no output schema and no annotations, the description covers purpose, traversal bounds, result filtering, and response shaping. It does not specify the exact result object shape, but the detail mode explanations give an agent enough to interpret the response. Minor gaps remain around what happens when max_nodes is exceeded or how warnings/errors are formatted.

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 description coverage is 0%, so the description must carry all parameter meaning. It does so comprehensively by explaining each parameter's role, default value, and valid choices, including the behavior of detail modes and the response_format options. This far exceeds the bare schema alone.

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 identifies the tool as a recursive walk that reports every node with cook, warning, parameter-expression, or script errors, and states that only problematic nodes are returned. This is a specific verb+resource pairing and the 'whole subtree' wording hints at the difference from the shallow sibling node_errors, though it does not explicitly distinguish itself.

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 gives useful context like the default root, recursion limits, and result filtering, so an agent can infer when a deep error scan is appropriate. However, it never explicitly says when to prefer this over node_errors or when not to use it, leaving sibling selection to inference.

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