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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds genuine behavior: results are constrained by a required typed relation rather than being a generic neighborhood dump. It does not disclose result caps (limit max 25) or what happens for an unsupported relation string, which keeps it below a 5.

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 core behavior is front-loaded in the first sentence, followed by a compact entity/relation map and a worked example - every clause carries vocabulary or disambiguation value. The telegraphic 'entity: a, b, c' notation is dense enough that it reads more like a legend than prose, which costs a point on clarity.

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?

With an output schema present, return values need no explanation, and the example payload correctly shows the three required fields in use. The remaining gap is the relation vocabulary: the entity enum lists 17 values but the map covers only 6, leaving an agent guessing for trial, phenotype, protein, and others.

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 50%, and the undocumented parameters include the critical required ones (relation, entity), so the description must compensate - and it largely does by enumerating valid relation values per entity. It leaves 'limit' and the free-form nature of 'relation' for uncovered entities unexplained, so the compensation is strong but incomplete.

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 opening sentence states a specific verb and resource ("List records linked to one record") and the rest resolves what a 'relation' means per entity type. It also explicitly distinguishes itself from get_record ("Record attributes are get_record sections, not relations"), so an agent can separate it from its closest sibling 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?

It gives an entity-to-relation map that tells the agent which relation strings are meaningful for gene, drug, disease, variant, article, and author, and it rules out one misuse case (using it for record attributes instead of get_record). It does not name alternatives for record fetching beyond that, nor explain what to do for the many entities (protein, pathway, gwas, patent, etc.) absent from the map.

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