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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, closed world), so the description's job is to add operational detail. It does: result ordering ('newest first') and the exact field set returned. It omits pagination/rate-limit behavior, but limit/cursor are schema-documented.

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 triggering question, then result shape, then filtering, then the sibling hand-off and the exclusion. Dense but every clause carries a distinct instruction; the run-on opening sentence is the only mild structural weakness.

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 no output schema, the description carries the return-value burden and does so concretely, enumerating the fields of a claim and giving a worked example (rapamycin extends_lifespan in Mus musculus). For a 7-parameter, annotation-covered read tool, this is complete enough to call correctly.

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 the schema already defines every filter with examples and match semantics (case-insensitive substring vs exact relation). The description's 'Narrow by subject, object, relation, organism or paper' largely restates that, adding only the news-first ordering context. Baseline 3 applies.

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: lists findings extracted from papers, rendered as subject/relation/object with organism, conditions, effect size and paper. It distinguishes itself from the sibling get_paper by framing this tool as the discovery surface and get_paper as the verification surface.

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?

Opens with concrete user-question patterns ('does an intervention extend lifespan, and in which organisms', 'what lowers a biomarker'), names the alternative (get_paper) with its selecting condition ('check a finding that matters'), and adds an explicit when-not ('Not for personal medical advice'). Nothing is left to inference.

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