query_graph

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

With no annotations provided, the description carries the full burden and does substantial work: it discloses that edges are aggregated ACROSS papers with verbatim evidence and source notes, that cross-paper agreement is surfaced as ×N, and that Path 2 is a recall fallback for missed relations. It omits auth requirements, rate limits, and result-size behavior, but the core behavioral model is well conveyed.

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 one-line purpose, then organized into labeled Path 1 / Path 2 sections and an Args block, so an agent can scan it fast. Slightly more verbose than needed, and defaults are restated from the schema, but nothing is filler.

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?

An output schema exists, so return-value shape needn't be re-explained, and the description covers both query paths plus all three parameters. It is complete enough to invoke correctly; the only shortfall is the absence of guidance on outcomes/limits that a no-annotation tool could have supplied.

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 0%, so the description must compensate, and it does: entity is given with concrete examples ('TXNDC5', 'TGF-beta', 'pulmonary fibrosis'), mode is enumerated with a default despite the schema lacking enums, and top_k is described as 'snippet notes to pull for the recall net' with its default. Minor gap: top_k's effect on Path 1 output is unstated.

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 verb and resource (knowledge-graph query for an entity) and decomposes it into two clearly named mechanisms: typed-edge retrieval with cross-paper aggregation and a verbatim snippet recall net. It also explicitly distinguishes Path 2 from the sibling search_snippets by noting it uses the 'same engine', so an agent can tell what this adds beyond that tool.

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 mode parameter is explained ('edges' | 'snippets' | 'both', default 'both'), which implies how to scope the query, and the recall-net rationale ('a relation the edge extractor missed is still surfaced') hints at when 'both' matters. However, there is no explicit when-to-use-this-vs-search_snippets guidance and no stated exclusions or prerequisites, leaving selection largely to inference.

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