summarize

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

Annotations are absent entirely, so the description carries the full behavioral burden. It does disclose what the tool computes (total size, file count, top-10 by extension), which is useful. However, it does not explicitly state that the operation is read-only/non-destructive, nor does it mention recursion scope or performance implications on large trees; '体检' only implies inspection.

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?

One short sentence that is densely informative and front-loaded with the purpose. Every element — total size, file count, top-10 extension ratio — earns its place, with zero 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 low-complexity, single-parameter tool with an existing output schema, the description covers the core behavior adequately. The gaps are meaningful but not severe: no tool-selection guidance against the scan siblings, and no explicit non-destructive/safety disclosure given the absence of annotations.

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%: the sole param 'dir' is already documented as a required absolute path in the schema. The description adds nothing new about the parameter, but none is needed at full coverage. 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 clearly states a specific verb-action ('目录体检' directory checkup) and resource (directory), and enumerates concrete outputs: total size, file count, and top-10 extension share. This distinguishes it from the scan siblings in terms of aggregation level, though it never explicitly calls out the overlap with scan_by_ext.

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 guidance on when to use this tool versus alternatives. The sibling tools scan_large, scan_duplicates, scan_by_ext, and scan_old are all plausible competitors, and an agent is given no criteria for choosing summarize over, say, scan_by_ext when extension breakdowns matter.

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