check_family_links

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

Annotations already declare readOnlyHint and openWorldHint=false, but the description adds real value: it confirms no mutation occurs, lists the specific defect categories found, and states each finding includes repair instructions. It stops short of describing output format or how limit truncation behaves.

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?

Front-loaded with the purpose, then a compact enumeration of findings and a terse 'Reports only' close. Every line earns its place, though the broken-line list reads a bit staccato rather than as clean prose.

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 read-only audit tool with no output schema, the description adequately conveys what a finding contains (a defect plus a repair hint) and that nothing is modified. It omits pagination/limit semantics, but those are covered in the 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 description coverage is 100%, so both parameters (limit, include_private) are fully documented in the schema. The description adds nothing about them, 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?

States a specific verb (audit) and resource (links between people and families, in both directions), then enumerates the four defect classes it looks for. This clearly distinguishes it from siblings like find_duplicates and verify_tree without needing 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?

'Reports only' tells the agent this is diagnostic, not a repair tool, which is useful context. But it never names an alternative (verify_tree, find_duplicates) or states when an agent should choose this audit over a general tree verification.

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