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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description usefully adds what the operation returns ('full file contents as text — CSV rows or a GeoJSON FeatureCollection...') and the exact fields included (DCPI score, target MW, market, coordinates, notes). It also flags the PRO entitlement gate. Slight deduction for not covering edge-case behavior like empty shortlists or large-result handling.

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 information-dense but every element earns its place: trigger phrase, mini-example, param summary, return type, and exclusions. It's a bit of a run-on wall of text—the em-dash stitching of example into a separate clause is awkward—but front-loads the trigger and uses scannable 'Params:' and 'Returns:' labels. A tighter restructure could earn a 5.

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 an output schema exists (so return-value shape need not be re-explained) and annotations carry the read-only/idempotent/destructive profile, the description covers the key operational needs: when to invoke, what format to request, what comes back, and which siblings NOT to use. Gaps—such as how empty shortlists behave or whether the export is synchronous—are minor given the output schema covers structured return details.

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 XSD: schema covers 100% of the single parameter with a clear description of 'csv' (default) and 'geojson' formats. The description reinforces this and adds a concrete usage example ('export_dataset format=geojson') plus a QGIS use case. This aligns with the baseline-3 expectation when schema already documents parameters well; the description adds a small but not transformative increment.

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 a specific verb+resource+scenario: 'pull their saved DC Hub shortlist OUT of the platform' for offline analysis. It goes further by naming and differentiating from siblings ('Do NOT use to list sites in-chat (use list_saved_sites)...'). An agent can immediately and unambiguously determine this is the bulk-download tool.

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?

Text explicitly states when to use ('Use when a user wants to pull their saved DC Hub shortlist OUT of the platform'), provides a concrete trigger example, and gives clear exclusions with named alternatives (list_saved_sites, save_site). Explicit exclusion of in-chat listing vs. saving directly routes an agent to the correct tool among 100+ siblings.

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