deep_check

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

The description thoroughly discloses behavior: fix parameter triggers repairs for anonymous_source and short_content; other checks are report-only even if fix is true. This adds context beyond the readOnlyHint annotation, which is false, and aligns with the described mutation when fix=true.

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 relatively concise for the complexity, with the purpose front-loaded in the first sentence. Some redundancy exists (e.g., listing checks twice), but it remains efficient.

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 tool behavior well, including fix vs. report-only and how to handle report-only issues via other tools. However, it lacks explicit mention of output format (e.g., returns a report/preview), which would make it fully 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?

Schema covers all three parameters (100% coverage). Description adds behavioral details: fix behavior for specific checks, checks parameter options listed explicitly, and explains that empty means all checks. This supplements the schema.

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 specifies a clear purpose: 'deep heuristic analysis of memory data quality'. It lists specific detected issues and distinguishes from sibling tools by detailing actionable checks and linking to other tools for non-repair actions.

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?

Explicit when-to-use guidance: explains that fix=true applies repairs to specific checks, while others are report-only with directions to use sibling tools (merge_memories, delete_memory, etc.) for those decisions. Also mentions checks parameter to select specific checks.

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