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

With no annotations, the description carries the full burden and does well: it discloses ranking behavior, that each hit carries its source paper, and the cost profile ("Free · 1 credit"), which is real decision-relevant context. It omits pagination/limit behavior and any error or empty-result behavior, so it is not fully complete for a 4-param search.

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?

Dense but front-loaded: purpose and scope come first, then filtering, then positioning, then cost. Every clause carries information, though the em-dash-heavy packing of the opening sentence makes it slightly harder to scan than it needs to be.

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 read-only search with no output schema and no annotations, the description covers what an agent most needs: what is searched, how results are ordered, what accompanies each hit, and the credit cost. The remaining gap is `limit`/result-volume behavior, which is undocumented in both the schema and the description.

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 50% and there are no enums, so the description's enumeration of valid types ("Paper, Method, Algorithm, Model, PerformanceClaim, Result") is genuinely load-bearing — it compensates for the missing enum on `types`. `topic_id` and `types` are already described in the schema, but `q` and `limit` remain unexplained in both places, keeping it below a 5.

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?

"Full-text search over an expert's graph nodes" gives a specific verb and resource, then enumerates the node kinds covered (claims, results, methods, datasets, metrics, papers) and the return shape (ranked hits with source paper). It also positions itself as "the entry point for node ids," which separates it from prose-answering siblings like expert_ask.

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?

It states a clear selection condition against a named alternative: use this "cheaper than expert_ask when you want facts, not prose." The "entry point for node ids" note further signals its role in a workflow. It does not address other plausible alternatives (e.g. library_search_nodes, expert_node_context) or state exclusions beyond the expert_ask contrast.

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