check_family_links

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine value beyond that: it confirms 'Reports only' (no auto-repair) and states that findings include repair guidance, which is behavioral context the annotations do not carry.

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?

Purpose is front-loaded in the first sentence, then the finding catalogue is presented compactly, and it closes with the one operational constraint that matters ('Reports only'). No filler sentences.

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 two-parameter read-only audit tool with no output schema, the definition covers scope, defect classes, repair guidance, and the non-mutating nature. Minor gap: nothing about result volume/truncation behavior when limit is hit, though limit's schema description mitigates this.

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%, so limit and include_private are fully documented in the schema itself. The description contributes nothing about parameters (e.g., whether limit truncates silently or what counts as one finding), so the baseline 3 applies.

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?

Specific verb+resource ('audit the links between people and families') followed by an enumeration of the four exact defect classes it detects. An agent can distinguish this consistency-check tool from siblings like verify_tree or find_duplicates without opening the schema.

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 scope is clear enough to know when to reach for it (link integrity auditing), and 'Reports only' signals it is a diagnostic pass rather than a fixer. However, it never names or contrasts with nearby siblings such as verify_tree, find_duplicates, or the various link-mutation tools, so the agent must infer the boundary.

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