cls_install_hooks

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

No annotations are provided, so the description carries full burden. It discloses that session_end is not needed, but does not state whether the tool modifies the repository, writes files, or merely outputs to stdout. The behavioral impact is unclear.

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 sentences, front-loaded with purpose, and free of extraneous information. Every sentence adds value, making it highly concise.

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 description covers the main purpose and outcome but lacks details on return format or side effects. Since there is no output schema, additional context about what is output would improve completeness. Still, it provides adequate high-level understanding.

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 baseline is 3. The description adds no additional meaning beyond the schema; it does not explain parameter context or usage scenarios. The schema already adequately describes each parameter.

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 it outputs a git post-commit hook and CI step for continuous learning, with specific verb 'output' and resource identification. It distinguishes its role from related tools like session_end, but does not explicitly compare with sibling tools like auto_learn_session.

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 usage context ('every git commit and CI build automatically feeds the brain') and says 'run once per repository', but lacks explicit guidance on when to use versus alternatives like session_end or auto_learn_session. No 'when not to use' advice.

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