Judges codebase architecture across eight axes, reporting doc staleness, redundancy, and split-ROI advice for oversized files.
Tree-scale structure judgment, eight axes (ce.structure-report schema).
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | judge the S5 doc-staleness axis over this window | |
| deep | No | also judge the S6 redundancy axis | |
| path | No | subpath (default: project root) | |
| split | No | price the split-ROI advisory for files past the soft line |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, yet it says nothing about whether this is a read-only analysis, whether it mutates anything, cost/latency of a tree-scale run, or what the eight axes evaluate. Only the referenced schema name hints at output shape.
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?
A single compact sentence with no filler and the schema reference up front. However it is under-specified rather than genuinely concise, and the jargon 'tree-scale structure judgment' costs clarity for the space it saves.
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?
No output schema exists, no annotations, four optional parameters, and an analysis tool whose axes are named only obliquely ('eight axes', 'ce.structure-report schema'). An agent cannot tell what the report contains or what each axis flags, so the definition is incomplete for the tool's complexity.
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 100%, so all four parameters (days, deep, path, split) are already documented in the schema, including which axis each toggles. The description adds no syntax, defaults, or interaction details beyond that, so the baseline 3 applies.
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 names a resource (structure) and a scope (tree-scale, eight axes) plus a report schema, so it is more than a tautology. But the operative verb is fuzzy ('judgment'), and nothing distinguishes it from siblings like architecture or scan that also analyze project structure.
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 when-to-use guidance at all: no prerequisites, no conditions, and no pointer to an alternative sibling such as architecture or scan. The agent must infer invocation context entirely from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.