deep_check

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

The description goes well beyond the readOnlyHint=false annotation by disclosing exactly which checks are repaired by fix=true, which are report-only, and that fix is accepted but ignored for those. It also surfaces the default dry-run preview behavior and the judgment call nature of the analysis.

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 dense but every sentence carries a distinct responsibility: scope, issue taxonomy, fix behavior, routing, and check selection. The core capability is front-loaded and there is no filler.

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?

For a tool of this complexity, it covers the input contract, per-check fix behavior, and downstream actions, which is strong. It does not describe the shape or content of the report returned (and there is no output schema), so an agent must assume the issue categories are the output vocabulary.

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 the baseline is 3; the description adds value by grouping checks into fixable vs report-only and by explaining that fix is not a global repair switch. It confirms how checks selects specific checks, though it does not add detail beyond the schema for session_key or agent_id.

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?

States a specific verb ('Deep heuristic analysis') and a well-scoped resource (memory data quality), then enumerates the six concrete issue categories it detects. This clearly distinguishes it from sibling health/update tools even without reading their schemas.

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?

It gives actionable guidance on how to use the fix flag and which checks to select, and routes report-only outcomes to the correct follow-up tools (merge_memories, delete_memory, calibrate_threshold, update_profile). It does not explicitly contrast deep_check with check_health or other diagnostic siblings, so an explicit when/not-when boundary is missing.

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