check_graph

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

With no annotations, the description fully discloses: it reports findings, with apply=true it deletes orphan relations and clears missing parentIds, but cycles are never auto-repaired. It does not detail response format or permissions, but the core behavioral traits are well-covered.

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 extremely concise, using two sentences to pack purpose, capabilities, and limitations. It front-loads the core detection task and immediately follows with conditions and caveats. No wasted words.

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 ideally characterize the report format. It only says 'Reports findings' without structure. It also omits safety or permission context, though the non-destructive default partially compensates. Adequate for a simple tool but not fully complete.

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% for the single boolean parameter 'apply', but the description adds value beyond the schema's simple 'repair' description by specifying exactly what actions are taken (deletes orphan relations, clears missing parentIds) and what remains unchanged (cycles). This clarifies the parameter's impact.

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 the tool detects orphan relations, missing parents, and hierarchy cycles, and optionally repairs the first two. This verb+resource combination is distinctive among siblings like validate_graph (which likely only validates) and detect_patterns (different focus).

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 explicitly says when to use: to detect/fix graph integrity. It notes the default dry-run behavior and, crucially, that cycles are never auto-repaired, guiding the agent on what not to expect. It lacks explicit comparisons to alternatives but the context is clear.

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