apply_plan

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

Annotations only convey readOnly=false, idempotent=false, destructive=true, and openWorld=true. The description adds substantial non-obvious behavioral detail: it applies only the host-authorized subset, the plan is immutable and current-process scoped, write mode is required, submission is rejected, and unknown outcomes are read back but never replayed. No contradiction with the annotations.

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?

Four short sentences, each carrying unique operational meaning with no filler. The action and constraints are front-loaded, and every phrase earns its place.

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 description covers safety, scope, and non-obvious constraints well, but there is no output schema and no explanation of what the tool returns or how the agent should monitor outcomes. 'Unknown outcomes are read back, never replayed' hints at behavior but does not fully equip the agent to handle post-apply verification.

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 does not explain planId, digest, operationIds, or authorization beyond vague phrases like 'host-authorized subset.' The agent must rely on parameter names and the schema's type/format constraints, which is insufficient for a required-parameter set of four.

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 ('Apply') and a specific resource ('host-authorized subset of an immutable, current-process domain plan'), and adds clear constraints that set it apart from the plan_* siblings: it executes a plan rather than generates one, rejects submission, and never accepts endpoints or plan-file paths.

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 provides operational guidance: requires write mode, rejects submission, and excludes endpoint/path inputs. However, it never explicitly names sibling tools or states a when-to-use/when-not-to-use rule, so the agent must infer that this tool is meant to be used after one of the plan_* tools.

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