Validate Memory References

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

The description states 'optionally auto-healing broken links', which implies a mutation or healing action, but the annotation readOnlyHint=true marks the tool as read-only. The auto_heal parameter's schema description says 'flag broken nodes with warning metadata', which does not match 'healing' and further confuses the behavior. This is a direct contradiction.

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 a single, front-loaded sentence with no redundancy. It conveys the primary action and the optional enhancement in a compact form.

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 tool has no output schema, so the description should clarify return values or operational outcomes. More importantly, the auto-healing behavior is ambiguous and contradicts the readOnlyHint annotation, leaving a significant gap in what the tool actually does. Annotations provide some safety context but do not resolve this contradiction.

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 description coverage is 100% (both project and auto_heal are described), so baseline is 3. The description adds meaning by linking auto_heal to 'auto-healing', but it does not clarify the discrepancy with the schema's 'flag ... with warning metadata'. The project parameter receives no additional semantic context.

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 a specific action ('Validate cross-memory references') and distinguishes the resource ('external file paths and code symbols'). The optional 'auto-healing broken links' adds a distinct capability that differentiates it from sibling tools like validate_graph or verify_requirement.

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 implies when to use the tool (for validating cross-memory references), but it does not explicitly state prerequisites, when to prefer this over alternatives, or any exclusions. Sibling tools like validate_graph could overlap, but no differentiation is provided.

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