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

No annotations exist, so the description carries the full behavioral burden. It does disclose a meaningful behavioral fact — the `grounded` flag records whether the quote matched the source verbatim — and implies a prerequisite (an already-ingested review). It says nothing about read-only nature, permissions, or pagination.

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?

Two dense sentences that front-load what the tool returns before listing filters. Little wasted wording, though the parentheses around `grounded` slightly interrupt the flow.

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 8 parameters, no annotations, and no output schema, the description does explain the return shape but leaves pagination (limit/offset) and the `space` scope unexplained, gaps that matter for an agent invoking this 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 coverage is 0% across 8 parameters, so the description must compensate. It maps meaning onto four of them (text→q, claim type→claim, PMID→pmid, grounding→grounded), but limit, offset, and space remain entirely undocumented in both schema and description.

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 states a specific resource with concrete return fields: evidence spans, quoted text, study, section, relevance, and the grounded flag. It clearly distinguishes itself from data-oriented siblings like records and studies. It stops short of naming which sibling to use instead for adjacent needs.

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?

"Filter by text, claim type, PMID or grounding" implies how the tool is meant to be narrowed but never states when to choose this over brainkb_synthscholar_records, _text, or _studies. Usage is inferable from the filters rather than explicit.

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