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

With no annotations provided, the description must carry the behavioral burden. It explicitly states 'Does not write the files; returns patches', which is a key non-destructive behavior. However, it does not disclose other potential effects, such as whether it modifies any internal state or what the exact format of 'patches' is. This is a partial disclosure but not comprehensive.

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 description is two concise sentences, front-loaded with purpose and key behavioral detail. Every sentence adds value; there is no fluff or redundancy.

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?

The tool has one optional parameter and no output schema. The description explains the purpose and the fact that it returns patches, but it does not elaborate on the structure of the patches or how they should be applied. Given the simplicity, it is mostly complete, but the lack of output format details is a minor gap.

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?

The schema covers 100% of the single parameter with a clear description ('Existing architecture.hexum so already-present forbids are omitted.'). The tool description itself does not add parameter details beyond the schema, but the schema is sufficient. 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 states a specific action ('synthesize'), a clear resource ('architecture.hexum forbid lines and SKILL.md directives'), and the context (from session violations). It also clarifies that it does not write files but returns patches, which distinguishes it from other hexum tools like hexum_check or hexum_expand. The purpose is unambiguous and differentiated.

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 implies the tool should be used when there are session violations, as it says 'From this session's violations'. However, it does not explicitly state when to use it versus alternatives, nor does it mention any exclusions or prerequisites. It gives context but no direct routing to this tool over siblings.

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