deep_check

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

The description discloses that the tool can apply repairs when fix=true, and defaults to a dry-run preview. This goes beyond the readOnlyHint annotation (false) by detailing the mutation behavior. No contradictions with annotations.

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 concise and front-loaded with the purpose. It covers all key aspects in a few sentences. However, it could be more structured (e.g., bullet points for the issue types) to improve scanability. Still, every sentence earns its place.

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 what the tool does and how to use it, but lacks details about the output/report format. Since there is no output schema, the description should specify what the tool returns (e.g., a list of issues with severity). This gap reduces completeness, especially for a diagnostic 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?

Schema coverage is 100%, so baseline is 3. The description adds value by explaining that near_duplicate and calibration_staleness checks are report-only, requiring other tools for action. This extra context improves understanding of the checks parameter beyond the schema's enum list.

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 the tool performs deep heuristic analysis of memory data quality and lists specific issues detected (anonymous sources, short content, stale profiles, etc.). It distinguishes itself from sibling tools like merge_memories, delete_memory, and calibrate_threshold by noting which checks are report-only and require those other tools for 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 guidance on when to use: it detects issues requiring recovery or judgment. It explains the fix parameter (default dry-run, set to true to apply repairs) and the checks parameter (empty runs all, otherwise select specific checks). It also clarifies that near_duplicate and calibration_staleness are report-only, directing users to sibling tools for decisions.

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