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

Annotations cover the read-only/idempotent safety profile, but the description adds far more: ~1 minute latency as the slowest tool, AI-generated SQL that should be checked before trust, an 8-second SQL execution limit, and a known silent-failure mode (per-day subqueries returning all-null rows) with the recommended workaround. These are exactly the non-obvious traits an agent cannot get from structured fields.

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 disambiguation and last-resort framing are front-loaded, and the performance/query-shape warnings follow in a sensible order. It is dense and long, but nearly every sentence carries a distinct operational constraint; only the queryable-tables list is somewhat list-like.

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?

With no output schema, the description still explains what comes back (SQL, rows, explanation). Combined with the table allowlist, latency and SQL-timeout limits, and the failure-mode warning, an agent has everything needed to decide whether to call it and how to phrase the question.

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% and the single question parameter already documents the plain-English format and a worked example. The description still adds meaning the schema lacks: scope each question to about one region-month, and request a window function for per-day top-N. Those are content-level constraints on the parameter, not restatements.

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?

States a specific verb+resource: it takes a plain-English question, generates SQL over NEMPulse's tables, and returns the SQL, result rows and an explanation. It also names the exact scope of queryable data and explicitly excludes the market analysis tables, so the agent knows precisely what this tool can and cannot do.

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?

Explicitly framed as a last resort for questions the other tools cannot answer, with two named alternatives (get_regional_prices for daily RRP, AEMO NEMWEB DISPATCHPRICE for the live 5-minute feed) and the condition that selects each. The exclusions are stated rather than inferred.

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