Check

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

Annotations already declare readOnlyHint=true, so the safety profile is covered and the description does not contradict it — the enumerated defect checks are consistent with a pure audit. Beyond the annotation, the description usefully discloses the exact categories of problems inspected, which is real behavioral context. It does not say whether all checks always run, whether findings block anything, or whether a report is written, though the output schema partly covers the result 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 sentence, front-loaded with the verb and resource, then a colon and a compact list of checks — zero filler and no repetition of the title. Density of domain jargon is the only cost, and it is not the result of padding.

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?

With readOnlyHint and an output schema present, the description does not need to explain safety or return values, and the parameter is fully documented. What remains a gap is scope ambiguity: 'hồ sơ' suggests a record/document while the parameter is the repo root, and the enumerated checks are not defined enough for an agent to predict what counts as a failure. Adequate, but not complete.

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?

There is exactly one parameter, project_dir, and the schema documents it fully ('Đường dẫn tuyệt đối tới gốc repo dự án' with 100% coverage). The description adds no further meaning about the parameter, which is expected at this coverage level; 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 specific verb ('Kiểm' = check/audit) and resource ('hồ sơ' = project record) and then enumerates five concrete defect classes it looks for: leftover frame variables, broken links, closed waves missing lessons-learned or still carrying 'Chờ' issues, wave-table drift, and decision-log drift. That is far more specific than a generic 'validate' tool and no sibling (status, read_guide, open_wave) covers the same audited artifacts. It stops short of 5 only because terms like 'biến khung sót' and 'wave' rely on internal jargon that an outside agent cannot fully resolve.

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 explicit when-to-use or when-not-to-use statement and no named alternative. Usage is only implied by the enumerated checks — an agent infers it should run this to audit project consistency, likely before closing a wave or finalizing. Nothing states whether this is a pre-commit gate, a periodic audit, or how it relates to the 'status' sibling.

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