session_health_check

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

With no annotations, the description carries full burden. It discloses that integrity checks are run and that auto_fix=true will mutate state (backfill embeddings, remove orphans). It does not detail rollback or impact on unrelated data, but covers the main behavioral traits.

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 well-structured: a summary sentence, a bulleted list of checks, and a final line about auto_fix. Every sentence adds information without redundancy.

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 diagnostic tool with one optional parameter, the description covers the checks and the effect of auto_fix. However, it lacks information about output (e.g., report or success message) and could mention if the checks are read-only by default. Overall sufficient given no output schema.

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% and schema describes auto_fix as boolean with default false. The description adds value by specifying what 'repair' entails (backfill embeddings, remove orphaned handoffs), which goes beyond the schema's text.

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 'Run integrity checks on the agent's memory' and lists four specific checks (missing embeddings, duplicate entries, orphaned handoffs, stale rollups). This distinguishes it from sibling tools like 'maintenance_vacuum' or 'session_compact_ledger' by focusing on health diagnosis.

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 explains what checks are performed and when auto_fix=true can be used to repair issues. However, it does not explicitly state when not to use this tool or suggest alternatives among siblings, leaving some ambiguity.

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