approve_table_selection

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

With no annotations, the description fully discloses behavioral nuances: the two distinct return paths, that all_offered_tables must come from generate_pipeline_sql, the warning that SQL is auto-generated and must not be validated, the instruction to 'Report the saved receipt and stop,' and the directive to pass sql/graph unchanged to save_pipeline_sql. This is rich, non-obvious behavior that the agent needs to know.

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 moderately long but every sentence contributes actionable information. It front-loads the core purpose in the first sentence, then uses short paragraphs for preferred usage, alternative usage, and a critical warning. No filler or redundant content—each line earns its place.

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, the description covers the essential context: it is the second step of a two-step flow, it has two operational paths with different return values, it explicitly states what to do with the returned data (hand to save_pipeline_sql unchanged) and what not to do (validate against metadata). The output schema exists but the description still summarizes the return payloads, making the tool self-contained.

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 0%, so the description must compensate. It clarifies the meaning of keep_tables and all_offered_tables (fully-qualified DB.SCHEMA.TABLE names, with all_offered_tables tied to generate_pipeline_sql's offered_tables) and explains the effect of save_to_version_id. However, it does not explain the remaining parameters (pipeline_id, knowledge_cluster_id, session_id, target_table, max_attempts), which are mostly self-explanatory but still lack explicit semantic guidance. The key ambiguous parameters are covered, so this goes above baseline 3.

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 opens with a specific verb-resource pair: 'Confirm the table selection and generate the SQL.' It explicitly identifies itself as 'Step 2 of 2,' clearly tying it to the preceding generate_pipeline_sql step, and distinguishes the two operational modes (with/without save_to_version_id). This removes ambiguity about the tool's role among the large sibling set.

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 gives explicit when-to-use and when-not-to-use guidance. It names the preferred path ('PREFERRED: pass save_to_version_id... the SQL is generated and saved in this single call') and the alternative path that requires handing sql/graph to save_pipeline_sql. It also names specific tools to avoid ('get_table_details or list_kb_tables') and explains why validating is wasted work, analogous to TDQS 4.3's explicit alternative naming.

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