graph_patch

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

With no annotations, the description carries the transparency burden and does well: it discloses that the server expands the patch into an atomic ChangeSet, preserves omitted fields, and can create a Block checkpoint. This gives useful behavioral traits beyond the schema, though it omits permissions, reversibility, and return behavior.

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 sentences with no fluff; the core action is front-loaded. The second sentence is a bit dense with three behavioral clauses, but it is still economical for the information it conveys.

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 mutation tool with 9 parameters, no output schema, and no annotations. The description explains the patch concept and atomicity but omits the meaning of most parameters, does not describe what the server returns, and leaves the checkpoint=auto mechanism unclear. An agent would need much more guidance to invoke this confidently.

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% across 9 parameters, so the description must compensate. It adds some meaning by describing the patch format as compact mdflow/1 Markdown-like and mentioning checkpoint=auto, but it does not explain task, actor, planId, reason, gitHead, projectRoot, chainScopeId, or includeStructured, leaving most parameters ambiguous.

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 action ('Apply') and a resource ('compact mdflow/1 Markdown-like patch'), and connects it to graph_mutate via the shared atomic ChangeSet. This clearly distinguishes it from the sibling tool and tells an agent what the tool fundamentally does.

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 relationship to graph_mutate is implied by saying it expands into the same atomic ChangeSet used by graph_mutate, but the description never explicitly says 'use this instead of graph_mutate when you have a compact patch' or lists exclusion conditions. The usage context is inferable, not stated.

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