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

With no annotations, the description carries full burden. It discloses that process records are never returned, relation_class defaults to epistemic, and run_id attribution behavior. It does not explicitly state read-only or safety, but search tools are generally safe; minor gap.

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 three sentences, concise and front-loaded with the primary purpose. Every sentence adds value with no redundant information.

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 tool with 7 parameters and no output schema, the description covers main functionality and key behaviors (process exclusion, relation_class defaults, run_id attribution). However, it does not describe the return format or pagination, which are important for a search tool given no output schema.

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 description adds meaning beyond schema: explains the purpose of kind, relation_class, and run_id in detail. It clarifies the default behavior for relation_class and the run_id attribution logic. However, some parameters like limit and subtype are not additionally explained beyond schema descriptions.

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 performs keyword search over the scientific graph across multiple kinds (claim/relation/activity/metric/bundle), and distinguishes it from methodist_search_semantic for semantic search. It also mentions that process records are excluded, further clarifying scope.

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 specific guidance: when searching relations, the default is epistemic set; pass relation_class for engineering/all. It also notes that for semantic search over claims, use methodist_search_semantic. However, it does not explicitly state when to avoid this tool entirely.

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