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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds value beyond them: 'Keyless' (no auth), the fact that it is a directory/reference listing, and the fields each facility carries including operational dates. It doesn't discuss pagination or result size, which is the remaining gap.

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?

Two sentences, front-loaded with the resource definition before the usage guidance, and no filler. The first sentence is dense with parentheticals (AGSI+ / ALSI+) but each clause carries information the agent needs.

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?

No output schema exists, so the description must convey returns, and it does: operator per country, facility name, type, EIC code and operational dates. With 4 optional params and no required ones, that's nearly complete; only pagination/result-size behavior is unaddressed.

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 enum for dataset is documented in-schema, so the baseline is 3. The description adds meaning beyond the schema by explaining that returned EIC codes are the join key used by the other GIE tools, which tells the agent why query matters. The country and include_closed semantics are left entirely to the schema.

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 the specific resource (directory of European underground gas storage sites and LNG terminals reporting to GIE), the fields returned (name, type, EIC code, operational dates), and frames it against sibling data tools by noting it supplies 'the EIC codes the other GIE tools filter on.' An agent can distinguish it from gie_gas_storage and gie_lng_terminals without opening a schema.

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 says when to use it: 'find which storage sites or LNG terminals a country has, or the EIC codes the other GIE tools filter on.' That's clear context and a routing hint to the sibling GIE tools, though it doesn't name those siblings directly or state when NOT to use it (i.e. prefer gie_gas_storage for time-series data).

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