Search knowledge

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and scope are partly covered; the description reinforces this with "Free, no side effects" and clarifies that peers' knowledge is included, matching the open-world hint. It also enumerates the returned row fields (id, name, price, rows, status, verification quorum, benchmark schema), which is useful. However, it says nothing about pagination limits, result ordering behavior, or what an empty result means, so it adds moderate rather than rich context.

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?

Four tight sentences, front-loaded with what the tool returns before the when-to-use guidance. Every sentence contributes; the field list is dense but justified because there is no output schema. Minor loss only from the slightly jargon-heavy framing of "memory-table patches."

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 nine-parameter, zero-required read tool with no output schema, the description covers purpose, return shape, cost, and a primary use case, which is enough to call it correctly in the common case. The main residual gap is guidance on the optional filters and paging, which the schema only partially documents.

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?

With nine parameters and only 56% schema description coverage, the description needs to carry real weight, but it only distinguishes browsing from searching (i.e., the query parameter's role). Filters like sort, limit, offset, status, origin, author, model, and schema are never mentioned or explained, leaving several parameters undocumented in both the schema and the 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 pairs a specific verb ("Browse or search") with a well-defined resource and even explains what that resource is: "trained memory-table patches a node applies into a running LLM." It implicitly separates bulk browsing/searching from the single-item sibling get_knowledge, but never names or contrasts with any sibling, so it falls short of the top tier.

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 gives a concrete triggering condition: "Use this first when the model gave a wrong or outdated answer and you want to find something that fixes it," which is genuinely actionable routing guidance. It stops short of explicit exclusions or pointing to alternatives such as get_knowledge for fetching a known item, so it is clear context without full when-not coverage.

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