patch_workflow

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

Annotations only declare destructiveHint=true, yet the description discloses transactional semantics (all-or-nothing, aborts before any GHL write), optimistic-concurrency behavior (detects external workflow changes via the version field), and an explicit non-guarantee (rewire_step does not validate for cycles or orphaned downstream steps; the caller owns flow correctness). That 'you are responsible for' framing is exactly the kind of hazard disclosure a destructive tool needs.

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?

Front-loaded with the core purpose before diving into op taxonomy and semantics, and every clause carries information. It is dense to the point of terseness in the 'Param roles —' fragment, and some op-list detail duplicates the schema's const values, which slightly dilutes 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?

For a destructive, no-output-schema mutation tool with a highly polymorphic operations array, the description covers purpose, op semantics, parameter roles, failure semantics, concurrency, prerequisites, and the escape hatch to a sibling. Nothing an agent needs to call this safely appears missing.

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 coverage is 100% so the baseline is 3, but the description adds real semantic value the schema cannot express: the subject-vs-anchor distinction between step_id and after_step_id, the step_id alias accepted by insert_after, and that next is a scalar pointer overwrite rather than a splice. The only gap is that per-op required-field combinations are left to the schema's anyOf.

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 verb (apply an ordered list of patch operations) on a specific resource (a workflow) with a stated mechanism (deterministic server-side pointer rewiring). It enumerates the exact op set and explicitly distinguishes itself from the sibling update_workflow for whole-workflow rewrites. An agent can select this over update_workflow without opening either schema.

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?

Explicit prerequisites ('Use after read_workflow_outline + read_workflow_step'), an explicit exclusion boundary ('For whole-workflow rewrites or branched-step splices, fall back to update_workflow'), and a pointer to the docs MCP for field meanings. This is the when/when-not/alternatives pattern at full strength.

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