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

With no annotations, the description carries the full behavioral burden, and it does disclose the domain values (title_abstract|full_text, include|exclude, abstract_only), the filter dimensions, and the aggregated counts returned by stage/decision/assessed_on/criterion. It omits explicit read-only framing, permission requirements, and pagination behavior implied by limit/offset.

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 what the tool returns and its field model, then the filter options, then the aggregate counts. Dense but each sentence carries semantic load; only the closing counts sentence borders on redundancy.

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 correctly explains the return payload (counts by stage/decision, assessed-on distribution, exclusion reasons by criterion). For a 10-param, annotation-free tool it covers the meaningful surface, though q, space, limit, offset and review_id are unexplained.

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 0% with 10 params and no enums, so the description must compensate, and it does for the core filters: it supplies the enum-like values for stage, decision and assessed_on, and explains reason matching by text or criterion code (e.g. "EC2") plus PMID. It leaves q, space, limit, offset and the required review_id undefined.

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 resource (the screening audit trail of an ingested review) and enumerates the decision/stage/reason fields it exposes, so an agent knows exactly what it retrieves. It doesn't explicitly contrast itself with nearby siblings like brainkb_synthscholar_records or brainkb_synthscholar_studies, leaving some overlap to inference.

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 tells you what you can filter by (stage, decision, assessed_on, reason, PMID, text, criterion code), which implies the retrieval scenarios. However it never states when to prefer this tool over the sibling records/evidence/studies tools, nor any exclusions or prerequisites.

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