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

Annotations already mark the tool as mutable/destructive and non-idempotent, and the description adds substantial behavioral context: monitors are stateful, management costs 0 credits while scheduled runs add a 1-credit premium, webhook delivery is signed, alerts and time-series accumulation exist, and a valid API key is required. This goes well beyond the annotation hints and gives the agent important operational expectations. No contradiction with annotations exists.

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?

Every sentence earns its place: core purpose, tagline, action enumeration, billing model, and auth requirement. The description is compact relative to an 18-parameter multi-action tool and front-loads the primary function before operational details. There is no fluff or repetition of schema content.

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 complex multi-action tool with no output schema, the description provides strong operational context including billing, auth, stateful behavior, and webhook signing. The parameter schema handles the detailed field semantics. The only notable gap is that the description does not explain the return shapes for list/get/runs/timeseries, which would be useful given no output schema is declared.

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 input schema covers all 18 parameters with descriptions, so the baseline is 3. The tool description reinforces high-level concepts like cadence, webhook delivery, alerts, and time-series, but it does not add per-parameter meaning beyond what the schema already provides. The schema itself carries the full semantic load for individual parameters.

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 opens with a specific verb and resource ('Create and manage stateful monitors') and immediately scopes the behavior: re-running recipes on cadence, delivering signed webhook results, raising alerts, and storing time-series. It lists all eight actions explicitly and distinguishes the tool from one-shot recipe execution via the tagline 'Prism answers once; monitors watch it for you.' This is clearly differentiated from siblings like socialcrawl_request.

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 clear context for when to use this tool: when a recipe must be re-run on a cadence, delivered to a webhook, or monitored for metric changes. It contrasts with one-shot execution using the tagline, and it clarifies billing implications. It does not explicitly name sibling alternatives or state hard exclusions, but the usage context is strong enough for an agent to select it correctly.

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