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

Annotations already declare readOnly/idempotent/openWorld, so the description's job is to add context, which it does: it discloses that results are IDs intended for a follow-up call, and that patent search is chemistry-linked (SureChEMBL) rather than bibliographic. It omits pagination/limit behavior, the summary-vs-full tradeoff, and cache/freshness behavior, which remain undocumented outside the schema.

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?

Front-loaded with the capability and entity list, then compressed routing notes, then an example — good ordering with almost no wasted words. The telegraphic fragments ('Papers: search_literature.') are efficient but border on unclear for a reader unfamiliar with the API.

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 7-parameter tool with an output schema, the description covers the entity enum, sibling routing, the follow-up call, and a concrete invocation example. Return-value detail is handled by the output schema and filter grammar by the input schema, so the remaining gaps are refinements rather than blockers.

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 only 43% and the schema encodes filter validity per entity only through verbose if/then blocks, so the description could add real value. It supplies one worked example (entity=gene, query=BRCA1, filters.species=9606) and a hint that source=patents is the assignee/inventor escape hatch, but it never explains which filters apply to which entity — the single most useful thing to add here.

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?

Opens with a specific verb plus an exhaustive enumeration of the record types searched (genes, proteins, drugs, diseases, variants, patents, authors, etc.), so an agent knows exactly what surface this covers. It also states the output shape ('returns IDs for get_record'), distinguishing it from siblings that return full records.

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?

Explicitly routes three adjacent intents away: papers to search_literature, trials to search_trials, and assignee/inventor/CPC patent queries to query_source(source=patents). It also names the downstream consumer (get_record for IDs, get_variant_evidence for variants), which is exactly the when/when-not guidance an agent needs.

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