Search Thumbgate

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

The readOnlyHint annotation already establishes that this is a safe read operation. The description adds contextual detail about the nature of the search (raw state across feedback, memory, rules, documents), which helps set expectations for the type of data returned. It does not describe output format or any side effects, but those are not necessary given the annotation coverage.

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 a single, information-dense sentence that front-loads the action and scope. It has no redundant words and every phrase ('raw', 'ThumbGate state', 'across feedback logs, ContextFS memory, prevention rules, and imported policy documents') contributes meaning.

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 moderate complexity (6 params, nested objects, no output schema), the description adequately frames when and why to use the tool. The schema handles parameter details, and the description covers the search domain and data sources. It doesn't explain result format or edge cases, but the tool is a search operation, so the information provided is sufficient for an agent to invoke it 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?

The input schema provides 100% description coverage for all six parameters, including enums, a nested filters object, and defaults like queryRewrite. The description text itself does not add parameter-specific meaning beyond the schema, so the baseline of 3 applies per the rubric.

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 identifies the tool's purpose: searching raw ThumbGate state across four specific sources (feedback logs, ContextFS memory, prevention rules, imported policy documents). The verb 'Search' is specific, and the scope distinguishes it from sibling tools like search_lessons or recall, which focus on different data domains.

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 provides clear context about what data the tool covers (ThumbGate state across named sources), which implies when to use it. However, it does not explicitly mention alternatives or when not to use it (e.g., 'for lesson search, use search_lessons instead'). The absence of exclusions and the clear scope justify a 4 rather than a 3.

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