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

With annotations covering readOnlyHint=true, idempotentHint=true, and destructiveHint=false, the description adds valuable context: it clarifies that retrieval is local and lexical, returns exact evidence and limitations, and does not store or echo the query. This goes beyond the annotations by describing the non-storing behavior and the lexical approach, which is helpful for agents to set expectations on privacy and retrieval style.

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?

The description is concise, with two sentences that are efficient and front-load the purpose. The first sentence states the action and resource, the second adds constraints and behavioral details. No wasted words, but it could be slightly more structured with separate sentences for clearer readability. It earns a 4 for being direct and informative.

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?

Given the tool's simplicity, annotations indicating a safe read operation, and an output schema (which presumably describes the return format), the description is fairly complete. It covers the query language constraint (Hebrew), the general nature of the query, and key behavioral limitations (no storage, no personal data). It could mention that it only searches approved public claims and bank guides, but it does. Minor gaps like parameter explanations are present but not critical.

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?

The schema coverage is 0%, meaning the description must compensate for undocumented parameters. The description explains the 'query' parameter by indicating it should be a short general Hebrew question)Skip with no personal details. However, it does not explain 'limit' or 'locale'. 'locale' has a default in schema (const 'he') but that's clear from schema. Since the description provides some context for the main parameter but leaves others unaddressed, a baseline of 3 is appropriate.

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 clearly states the tool searches approved public claims and bank guides using a short general Hebrew question. It specifies the input type (short general Hebrew question) and the scope (public claims and bank guides), distinguishing it from sibling tools like search_mortgage_knowledge which likely searches broader mortgage knowledge. The purpose is specific and concrete.

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 clearly indicates when to use this tool: when the user asks a general question about public claims or bank guides, and provides constraints (no personal details, numbers, links). It implies the tool is for public information retrieval, contrasting with sibling tools like get_claim or get_guide which may fetch specific claims. However, it does not explicitly state when not to use it or name alternatives, but the context is sufficient for an agent to infer usage.

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