extract_table_dependencies

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

No annotations exist; the description carries the full burden for behavioral disclosure. It fails to mention that the tool is likely read-only, lacks performance notes (scanning could be heavy), and does not describe side effects or data returned. The description is silent on all behavioral traits.

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 only two sentences and front-loaded with the core purpose, which is concise. However, it omits crucial details given the tool's complexity (10 parameters, no output schema). It is under-specified rather than efficiently comprehensive.

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?

This tool has high complexity (10 parameters, no output schema, many sibling tools), but the description provides almost no contextual completeness. It does not explain the output format (graph?), default behavior when no widget_id is given, or how the results relate to choices. Overall, it is inadequate for an agent to use effectively.

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 only 20%, but the description adds no parameter explanations. Only 'widget_id' is referenced casually. The other 9 parameters (e.g., 'page_size', 'include_business_rules', 'max_records_per_source') are left undocumented, leaving the agent to rely on parameter names alone, which may be ambiguous.

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 states the tool extracts a 'GlideRecord table dependency graph' from server scripts (SI/BR/widgets), and mentions limiting to one widget via widget_id. This conveys the main action and resource, but the acronyms (SI, BR) are not expanded, which mildly obscures clarity. It does not clearly differentiate from sibling tools like 'manage_widget_dependency'.

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 provides minimal guidance: 'Pass widget_id for one widget' implies scope-wide by default. No explicit when-to-use, when-not-to-use, or comparison with sibling tools (e.g., 'audit_local_sources' or 'search_server_code'). No context about prerequisites or output interpretation.

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