propose_index

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

With no annotations provided, the description carries the full burden, and it excels. It discloses that results are simulated, with evidence_level 'simulated', and explicitly names limitations (write amplification, regressions on other queries, real timings unknown). It further warns not to present candidates as advice. This is thorough behavioral disclosure beyond any default expectations.

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 well-structured: a concise opening sentence establishes the core purpose, followed by a clearly separated warning block that earns its place. Every sentence provides critical context (simulated evidence, limitations, alternative tool, usage caution). No fluff or redundancy.

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 complex tool with output schema and no annotations, the description is remarkably complete. It covers the action, the methodology (HypoPG, pg_stats, typical/worst/selective cases), the evidence level, and the critical caveats. The output schema handles return-value details, so no further description is needed there. It also situates the tool among siblings by naming verify_index.

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%, and the description does not compensate by explaining what each parameter (sql, profile, queryid) means or how they relate to the tool's operation. While the names are somewhat intuitive, the description must add meaning beyond the schema, especially with 0% coverage. It mentions 'for a query' and 'parameter values' but never links these to the actual input parameters.

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 function: generating candidate indexes and cost-simulating them with HypoPG, using pg_stats-grounded parameter values. It explicitly distinguishes itself from verify_index, which is the only tool that produces a real accept/reject verdict. This is a specific, actionable purpose with clear differentiation from siblings.

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 usage context: this tool is for simulated exploration only, not for final recommendations. It states clear when-not-to-use conditions (write amplification, regressions, real timings unknown) and points to verify_index as the alternative for real-data measurement. This is excellent guidance on when to use versus alternatives.

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