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

With no annotations, the description carries full responsibility for behavior; it does disclose the upsert-style mutation and the manual-only constraint with FORMULA rejection. It does not mention auth requirements, idempotency behavior, revision handling, or what happens on conflicting writes, leaving some behavioral 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?

Two tightly written sentences with no wasted words; the key constraint (manual and FORMULA-rejected) is front-loaded. It could be slightly expanded to cover parameter meaning without sacrificing conciseness.

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 9 parameters, no output schema, and no annotations, the description is too thin to let an agent invoke the tool correctly with confidence. It makes the purpose clear but omits parameter roles, revision/conflict behavior, and return expectations.

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, but it only adds meaning for edgeType by restricting to SOURCE, FLOW, or INTERFACE and rejecting FORMULA. Parameters like edgeId, fromId, toId, condition, label, owner, id, and rev are left entirely unexplained by the description.

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?

States a specific resource (manual edges) and operation (create or patch), and enumerates acceptable edge types (SOURCE, FLOW, INTERFACE) while explicitly excluding FORMULA. This clearly distinguishes it from sibling tools like model_upsert_observation and model_upsert_parameter.

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 implies this is the tool for creating or modifying edges, and the FORMULA exclusion tells the agent what is not allowed. However, it does not explicitly mention alternatives (e.g., model_list_edges for listing, model_delete_edge for deletion) or state conditions that would make another tool preferable.

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