search_materia_medica

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

No annotations are provided, so the description carries the behavioral burden. The description explains what materia medicas are and the tool's purpose but doesn't disclose return behavior, volume of results, or what happens when no matches are found. The output schema exists which helps, but for a search tool with no annotations, richer behavioral context (e.g., result format, default filtering) would help.

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?

Three sentences, reasonably compact, and front-loaded with the core purpose. The second sentence ('Materia medicas provide detailed descriptions...') adds helpful context for a knowledge domain that may be unfamiliar. Slightly redundant but not wasteful.

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?

With a 100% schema coverage, an output schema, and a reasonable description that orients the agent to the domain, this is fairly complete. The description explains the domain value, the parameters are well-documented in the schema, and an output schema exists. The main gap is the lack of alternative-tool guidance (search_repertory contrast).

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 description coverage is 100%, so the schema already documents all four parameters thoroughly with clear descriptions and examples. The tool description adds minimal parameter context beyond the schema. Baseline 3 is appropriate since the schema does the heavy lifting and the description doesn't need to duplicate it.

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 states the verb (search), resource (materia medica texts), and outcome (matching remedy sections). It adds context about what materia medicas provide ('detailed descriptions of remedy characteristics, symptoms, clinical applications'). However, it could better distinguish from sibling search_repertory - the description notes it's 'useful for in-depth remedy study and comparison' but doesn't explicitly contrast with a repertory search.

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?

No explicit when-to-use or when-not-to-use guidance, and no alternative tools are named. The description implies usage through context ('useful for in-depth remedy study and comparison') but doesn't tell the agent when to prefer this over search_repertory or get_remedy_info. Sibling differentiation must be inferred rather than stated.

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