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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds useful behavioral context: the data is sourced from GNERC's actual-balance workbook, covers 2015-2026, is in million kWh, and 'Station names are published in Georgian script; each row keeps its original name and its position in the balance hierarchy.' This goes beyond the annotations by describing the data provenance and naming convention, which helps the agent interpret results. No contradiction with annotations.

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 a single well-organized paragraph that front-loads the core content ('Monthly electricity generation...'), then adds scope, source, time range, units, and naming notes. It is concise without unnecessary fluff, and each sentence adds meaningful context. It could be slightly more structured with explicit headings, but it is appropriately sized and readable.

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 complexity of the data (multiple station types, national aggregates, hierarchy) and the absence of an output schema, the description covers key aspects: data source, time range, units, included entities, and the naming convention. It does not describe the response structure (e.g., columns or pagination behavior), but the limit parameter is documented. The description provides enough context for an agent to know what to expect and how to query effectively, though a bit more detail on response format would be ideal.

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 100% — all three parameters (year, limit, query) have descriptions in the schema. The description adds minimal extra beyond the schema: it clarifies the units (million kWh) and reiterates the Georgian script for station names, which is already in the query parameter description. Since the schema fully documents the parameters, a baseline of 3 is appropriate; the description does not significantly enhance parameter understanding.

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: 'Monthly electricity generation for individual Georgian power stations' plus national supply, consumption, import/export, and named consumers. It specifies the resource (generation data) and the scope (Georgian power stations), which distinguishes it from siblings like gnerc_prices (prices) and gse_* tools (grid data). The verb 'generation' and the explicit enumeration of stations and aggregates leave no ambiguity about what the tool returns.

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 detailing the data source (GNERC actual-balance workbook), time range (2015-2026), and content (generation, supply, consumption, etc.). However, it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or alternative tool names. The agent can infer relevance from the data scope, but there is no direct guidance on when not to use it.

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