check_knowledge_quality

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

The description explicitly states 'Read-only. Does not modify any files or the vector index.' This is critical behavioral info. Since no annotations are provided, the description fully bears the burden and addresses it well. It also explains return format with quality score and issue categories.

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 well-structured with a summary, usage guidance, and parameter/return details. Every sentence is informative; no fluff. It is appropriately sized for the tool's complexity.

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?

Given one simple optional parameter and no required params or nested objects, the description is thorough. It explains behavioral aspects, usage context, and return format. Lacks mention of error handling or edge cases, but sufficient for a read-only validation tool.

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 one optional parameter 'project'. The schema has no description (coverage 0%), so the description's mention 'Target project name (optional)' adds meaning. However, it does not elaborate on default behavior or domain, which could be valuable.

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 'Validate the knowledge base for consistency and structural correctness' using a specific verb and resource. It distinguishes from siblings by referencing validate_doc() and get_index_stats(), providing clear differentiation.

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 explicitly advises when to use: 'Use periodically or after adding many documents to spot quality regressions.' It also gives alternatives: 'Use validate_doc() instead to check a single document before committing. Use get_index_stats() to check chunk counts rather than quality.'

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