tong_hop_audit

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

With no annotations, the description must carry the burden. It does disclose two useful traits: the tool is file-based (no IFC input) and reads prior audit outputs, and that the project name must match a previous run (an implicit failure mode). It says nothing about whether a file is written or a report sent to the lead, nor about error behavior when no prior audit exists.

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?

Purpose is front-loaded in the first two sentences, followed by a compact Args block whose lines each add value (allowed values, defaults) rather than restating type information. No 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?

An output schema exists, so return values needn't be described, and parameters are covered. Missing is what "gửi cho lead discipline" actually means operationally (does it write a file, emit a report payload, or nothing beyond the return value), which matters for an aggregation tool with no annotations at all.

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 compensate — and it largely does, documenting all four parameters including the discipline and stage value sets (KT/KC/MEP/ALL, TKCS/TKKT/TKTC/AS-BUILT), the top default of 10, and the matching constraint on project. The abbreviations (KT, KC, TKCS…) are left unexplained, one notch below full marks.

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?

States a specific verb and resource: aggregates IDS + LOD + QTO results from a results folder into a summary for the lead discipline. It implicitly distinguishes itself from the per-check siblings (kiem_tra_ids, kiem_tra_lod, boc_khoi_luong) by being the aggregator, but never names them explicitly.

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?

"Không cần file IFC — đọc từ các file audit đã chạy trước" gives a real precondition (the individual audits must already have run) and implicitly positions this as a follow-up step. However no sibling is named and no explicit "use this instead of X when…" routing is offered.

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