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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds non-obvious behavior beyond that: results are paginated and next_offset should be passed back as offset, plus the dependency on get_esg_metadata for valid domain values.

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?

Three compact sentences, each earning its place: scope, usage, pagination mechanics, and prerequisite. Front-loaded with the resource definition and no 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 filtered, paginated list tool with an output schema (so return values need no prose) and annotations covering the safety profile, the description covers everything an agent needs: what it returns, how to page, and where to get valid domain inputs.

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%, so the baseline is 3. The description adds real value by explaining the pagination contract (next_offset -> offset) and by directing the agent to get_esg_metadata to obtain legal domain values, which the schema's example does not supply.

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 and resource ('List curated external ESG resources') and enumerates what the collection contains (standards bodies, regulations, tools, databases) plus the payload (source URLs). This is clearly distinct from get_* siblings, though it never names an alternative like search_esg, so it stops short of full sibling differentiation.

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?

Gives concrete usage context ('find authoritative references by domain or title') and a hard prerequisite ('Call get_esg_metadata first for valid domain values'). It does not state when NOT to use it or contrast it against search_esg, so it lacks the exclusions that would push it to a 5.

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