graph_edits

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

No annotations are provided, so the description carries full behavioral disclosure burden. It reveals that the tool performs mutations (WRITE), warns about unreliable temp-id maps, and advises against retrying. This goes beyond basic schema info, though it does not cover other traits like idempotency or atomicity.

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 extremely concise and front-loaded with 'WRITE.' Every sentence adds value: the operation list, the note about POST, and the crucial warning. No redundancy or filler.

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 the presence of an output schema, the description does not need to detail return values, but it does warn about the id-map unreliability. However, it does not fully describe the input parameter format, which is critical for a tool with only one parameter. The warning is helpful but the incomplete parameter documentation limits completeness.

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?

With schema description coverage at 0%, the description must compensate. It lists the operation types but does not explain the required structure of the JSON array or the fields for each operation. This leaves the agent with insufficient detail to construct valid input.

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 'WRITE' and 'Apply graph edits', listing all supported operations. It distinguishes from graph_records by noting that records are created via edits, not via a separate POST endpoint.

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?

Provides explicit guidance on when to use: to apply graph edits. The warning about retrying when no temp-id map is present gives clear post-invocation behavior, and suggests reading back with graph_records to reconcile. However, it does not explicitly state when not to use this tool.

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