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

The annotations already declare destructiveHint=true and idempotentHint=true, so safety is partly covered, yet the description still adds real behavioral context beyond them: that the recipe is fully replaced and that the previously reviewed sample is invalidated. That invalidation consequence is a genuine side effect an agent must plan for. It does not mention auth/permission requirements or whether the invalidated sample must be re-approved before activation.

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?

Three short sentences, action and consequence front-loaded, no filler. Each clause carries information. The final clause is slightly terse/ambiguous ("the saved automation type must match this tool") but does not waste space.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The description covers scope and side effects adequately. But for a five-required-parameter mutation with a large nested recipe object and 0% schema description coverage, it is incomplete on the parameter side and does not mention the revision/concurrency or idempotencyKey semantics an agent must supply correctly.

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 all five required top-level parameters, and the description supplies no parameter guidance at all. Nothing explains revision, idempotencyKey, or the structure of the recipe object. The one hint, "the saved automation type must match this tool," loosely relates to the recipe/type constraint but does not compensate for the coverage gap on a deeply nested schema.

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 names a specific verb and resource ("Replace this automation's recipe") and adds a concrete consequence ("invalidate its reviewed sample"), so the agent knows exactly what the call does. It differentiates itself behaviorally from the sibling generate_/activate_ tools by stating it does not generate or publish. It stops short of naming a specific alternative, but the purpose is unambiguous.

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?

Usage is implied through exclusions: "Does not generate or publish" and "Only generated logo concepts; the saved automation type must match this tool" tell the agent this is a config-edit tool for an existing automation, not a generator. However, it never names the alternative (e.g., generate_logo_maker_automation_sample for producing output, or prepare_logo_maker_automation for creating one), leaving the agent to infer routing from sibling names alone.

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