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

Annotations already mark the tool as read-only, non-destructive, and idempotent abstract. The description adds behavioral context beyond that by noting derivations are 'computed on-the-fly' from Tier-2 Parquet endpoints, and by clarifying the quirk that the JSON response calls 'capture rate' by 'quality_factor'. The 'Today:' qualifier also signals the set of derivations may evolve.

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 front-loaded with the core purpose and then gives a detailed but purposeful enumeration of the available derivations. It is longer than a simple list, but each parenthetical adds meaningful semantic value, such as unit context, IPCC factors, and zone behavior. It could be restructured for readability, but no sentence is filler.

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 parameterless catalog tool with a rich output schema And annotations, the description is complete: it names every current derivation, explains what they compute, relates them to get_derivation(), and flags naming quirks. An agent has enough context to call the tool and interpret the returned derivation names.

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?

The tool has zero parameterscm in its input schema, so the baseline is 4. The description does not need to explain parameters; it instead documents what derivations will appear, which is the relevant semantic content for a list operation. The passing mention of zone='all' for tb_spread is about a derivation's behavior via get_derivation(), not about this tool's 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 opens with the specific verb 'List' and the resource 'computed-metric derivations available via get_derivation()', which is a concrete, non-tautological statement. It also distinguishes itself from sibling tools by framing its output as the catalog of derivations used by get_derivation, not as endpoints or data series.

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 makes the usage context clear: use this tool to see which computed-metric derivations exist for get_derivation(). It does not explicitly state 'use this before calling get_derivation' or contrast with list_endpoints, but the connection to get_derivation and the enumerated list strongly implies the intended workflow.

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