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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds useful context about ELI inclusion and eId scoping, but it does not describe pagination behavior or the shape of the response beyond 'references with ELI where linked'.

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 one efficient sentence with the core action front-loaded. The only flaw is the trailing 'hint.' token, which is noise and does not contribute meaning.

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?

The schema documents every parameter, and the annotation covers the read-only nature, so the description does not need to repeat those. It tells the agent what the tool returns (references with ELI where available) and when to use it. A small gap is the lack of explicit pagination/continuation context, though the offset parameter description partially covers that.

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%, so parameters are already well documented. The description adds the eId scoping idea, but it mostly restates what the schema already explains; the baseline of 3 is appropriate.

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 names a specific verb ('List'), a specific resource ('references an act's text makes'), and a key feature ('with ELI where linked, optionally within one eId'). It is distinct enough from siblings like get_citations or parse_reference because it describes outgoing references from an act, and even states the intended use of following cross-references.

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 explicitly says 'use to follow cross-references,' which provides clear usage context. It does not name exclusion criteria or alternatives, but the stated purpose is enough for an agent to understand when this tool fits.

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