graph_mutate

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

With no annotations, the description carries the behavioral disclosure burden, and it reveals important traits: atomicity, Decision scoping that never enters Block/Chain/Plan coverage, the distinction between architecture-only create_block and verification-oriented create_checkpoint, and the need for expectedRevision on updates. It does not cover error behavior, permissions, or reversibility, but what it does disclose is meaningful and non-obvious.

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 dense but not bloated, with the core atomic create/patch purpose stated first and critical distinctions front-loaded. Each sentence adds useful information, though the entity list is long and could overwhelm a quick scan.

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?

This is a high-complexity tool with 9 parameters, 27 possible action types, no output schema, and no annotations. The description provides essential high-level guidance but does not explain required fields per action, how operations should be structured, what reason means, what projectRoot and chainScopeId refer to, or what the response contains. An agent would likely struggle to construct a correct call beyond the simplest create_block case.

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 sparse schema, and it partially does by listing allowed link kinds and explaining expectedRevision for updates. However, many parameters such as reason, projectRoot, chainScopeId, task, actor, and the structure of operation fields are left unexplained, leaving significant gaps.

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 uses a specific verb ('create or patch') and clearly enumerates the affected resource types: Blocks, Decisions, Links, Chain paths, Plans, Checkpoints, Background scopes, Decision scopes, and source refs. It also clarifies a key semantic boundary ('Decisions are not Canvas Blocks'), though it does not explicitly distinguish graph_mutate from the sibling graph_patch.

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 concrete when-to-use guidance for sub-operations, notably directing agents to use create_checkpoint when a requirement, Plan, Chain gate, or verification request makes a check necessary, while plain create_block only records architecture. It also advises keeping calls small and providing expectedRevision for updates, though it does not discuss when to prefer graph_mutate over graph_patch.

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