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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation nature is known. The description adds nothing beyond restating the operation and the raw HTTP route — no auth requirements, no side effects (signals, emails, webhooks triggered by the optional flags), and no rate-limit or validation notes.

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 short, front-loaded sentences with no filler or repetition. It is economical, though the brevity borders on under-specification for a tool with this many fields.

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 high-complexity creation tool with a large nested body, no output schema, and conditional field dependencies, the description covers none of the domain context (what an LLM reaction is, how it links to a data webhook and LLM API key, what creating it triggers). The schema fields carry the load, but the definition is too thin for the tool's complexity.

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?

The top-level schema has a single body parameter with no description (0% coverage), but the nested properties are individually well documented in the schema itself, including conditional requirements like 'required if use_chart is true'. The description adds no parameter meaning, so it neither compensates nor detracts.

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 and resource ('Create a new LLM reaction'), and the endpoint path confirms the target collection. However, it gives no differentiation from close siblings such as post_strategy_reaction_llm_duplicate or post_strategy_reaction_code, so the agent must infer which tool applies.

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?

There is no guidance on when to use this tool versus the duplicate/code-folder siblings, nor any prerequisite information. The description does not mention that llm_api_id, data_webhook_id and prompt are required, leaving the agent to discover this only from the schema.

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