create_erd

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

With no annotations provided, the description carries the full burden of disclosing behavior. It does disclose login requirements for server saves and workspaceId, and explains the local/file vs server distinction. However, it omits details such as whether an existing file gets overwritten, what response is returned, or the mutual exclusivity of sql/dbml (though schema covers that). The transparency is adequate but has clear gaps.

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, front-loaded with the core purpose and then efficiently covering the key behavioral variants. Every sentence adds useful information with no fluff or repetition, making it appropriately concise.

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?

Considering the tool's complexity (6 parameters, nested target object, no output schema, no annotations), the description covers the main usage scenarios: source, target, workspace binding, and auth requirements. It does not explain the 'name' parameter or return details, but these are either self-evident or covered by schema. The description is sufficiently complete for an agent to understand the tool's primary behavior.

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 already provides descriptions for 5 of 6 parameters (name is only missing). The description adds meaningful semantics beyond the schema, especially for target (local file vs server) and workspaceId (binds to naming standard, requires login). It also clarifies the 'empty or from SQL/DBML' source options, which maps to sql/dbml. This adds value beyond structured fields.

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 'Creates a new ERD' and specifies the source options (empty, SQL, DBML) and target modes (file, server). However, it does not explicitly distinguish this from sibling tools like import_sql or import_dbml, which could also create ERDs from SQL/DBML, so it lacks full sibling differentiation.

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 on when to use the tool: for creating a new ERD, with explicit choices for local vs server save and workspace binding. It does not mention alternatives or exclusions (e.g., when import_sql/import_dbml would be more appropriate), but the core usage scenarios are well explained.

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