sd_apply_graph_patch

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

The annotations only state that the operation is not read-only, not idempotent, and not destructive. The description adds value by specifying the patch is 'additive' (non-destructive) and that it rolls back on failure, providing important safety context beyond what annotations indicate.

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?

A single front-loaded sentence contains no filler. The verb 'Apply' immediately conveys the action, and all terms ('preflighted', 'additive', 'rollback on failure') contribute meaningful context.

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?

The presence of an output schema means return values don't need to be described, and annotations cover safety flags. However, for a complex mutation tool, the description does not mention preconditions beyond 'preflighted', relationships to validation tools, or specific failure handling semantics beyond rollback. It is adequate but minimal.

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%, and the description provides no parameter information. It fails to explain the structure of 'graph' or 'patch', leaving the agent to rely solely on the detailed schema. With zero coverage, the description had a responsibility to compensate, which it does not.

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 action ('Apply') and the resource ('preflighted additive graph patch'), and it distinguishes the tool from the sibling sd_validate_graph_patch by focusing on the application step. The phrase 'with rollback on failure' adds specificity about the behavior.

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 word 'preflighted' implies the patch should already be validated, but the description does not explicitly mention using sd_validate_graph_patch first or when to choose this over alternatives. Usage is only implied, not spelled out.

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