get_concept

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

Annotations already declare readOnlyHint=true, but the description goes further by stating 'nothing is ever generated' – a strong behavioral guarantee. It also discloses how unknown keys are handled (structured not_found with nearest keys) and that the tool is workspace-free (identical corpus across workspaces). These are significant behavioral details beyond the annotation.

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 moderately long but every sentence adds value: it lists return components, explains unknown-key behavior, and notes workspace invariance. It is front-loaded with the core purpose and avoids fluff. It could be slightly more concise, but it is well-structured and 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 no output schema, the description adequately explains what the tool returns (authored body, citations, related terms, flag) and handles edge cases (unknown keys). It also clarifies the workspace-free nature. It does not specify the exact structure of the response (e.g., field names) but that may be inferred. The main missing piece is parameter format guidance, which was already penalized in parameter semantics. Overall, it is reasonably complete for an agent to use 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?

Schema description coverage is 0%, so the description must compensate for the parameters 'key' and 'locale'. The description mentions 'one Begriff in one locale' and 'key' implicitly, but it does not explain what constitutes a key or the valid values/format for locale. The agent is left guessing about how to specify the locale or what a key looks like. This is a clear gap given zero schema documentation.

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's function: 'Read one Begriff in one locale' and enumerates exactly what is returned (authored body, statutory citations, related terms, not-implemented flag). It also distinguishes itself from list_concepts by focusing on a single term, though not naming the sibling explicitly. The verb 'read' plus the resource 'Begriff' makes the purpose unambiguous.

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 gives clear context: this is for retrieving a single concept's details, and it explicitly advises citing the authored body rather than paraphrasing, which guides the agent's use of the result. It does not name alternative tools or provide exclusion criteria (e.g., when to use list_concepts instead), but the scope is clear enough that an agent can infer it is for single-lookup use.

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