fix_broken_visuals

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

No annotations are provided, so the description carries the full burden. It thoroughly details what gets rewritten (prototypeQuery, projections, sorts, filters, conditional formatting/chrome bindings, page/report filters) and what it returns (one row per changed target, lists unmatched keys). This is strong disclosure, though it could add explicit side-effect or irreversibility warnings.

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 but comprehensive. It is front-loaded with the main purpose, then the repairMap format, then the detailed list of what is rewritten, and finally the return behavior. No unnecessary words, every sentence serves a purpose.

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?

Given the tool's complexity (many binding types) and the absence of an output schema, the description is quite complete. It lists all affected binding areas, explains the return value, and mentions unmatched key handling. It also references scan_broken_refs and set_visual_fields for context, making it sufficient for an AI agent to use correctly.

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 50% (only repairMap is documented). The description adds value by clearly explaining the repairMap format ('Old Table[Old Field]' to 'New Table[New Field]'), similar to the schema but with more context about its role. It does not explain reportSessionId, but that parameter is likely self-evident from its name, so the description adequately compensates for the coverage gap.

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's purpose: 'Repair visual bindings that point at RENAMED or MOVED model fields'. It specifies the resource (visual bindings), the action (repair), and the context (found by scan_broken_refs), which distinguishes it from siblings like scan_broken_refs and set_visual_fields.

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 usage context by referencing 'found by scan_broken_refs' and mentions it rewrites the same binding paths as set_visual_fields. This gives clear guidance on when to use it, but it does not explicitly state alternatives or exclusions beyond the implied workflow, so it earns a 4 rather than a 5.

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