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

With no annotations provided, the description carries the full burden, and it delivers the key traits: it discloses that Claude/AI is invoked ('Run Claude'), that nothing is persisted ('WITHOUT persisting anything'), and what the output is. It stops short of a 5 because it does not address indirect effects such as credit consumption, latency, or failure behavior when the agent has no script — though for a read-only preview, the no-persistence statement is the critical disclosure.

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?

A single dense sentence that front-loads the action and output, adds the critical side-effect disclaimer (WITHOUT persisting anything), and closes with a routing instruction. Every clause earns its place; no filler, no repetition of the title.

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 single-parameter, no-output-schema tool, the description is nearly complete: it enumerates the return components (partially compensating for the missing output schema), states the non-persistence guarantee, and gives the follow-up step. The only gaps are the slightly ambiguous 'review/edit' workflow phrasing and silence on credit/latency implications of running Claude, which matter in this credit-heavy tool ecosystem.

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 0% and the schema only says agent_id is a required string, so the description must compensate. It partially does by tying the parameter to 'the agent's script' being executed, and agent_id is self-descriptive among many agent tools. However, it never explicitly states that agent_id selects the agent to preview, how to obtain valid ids, or any format/ownership constraints, leaving the mapping to inference.

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 phrase ('Run Claude on the agent's script and return the auto-generated ICP profile') with concrete deliverable components (offer summary, ideal customer profile, relevant topics, LinkedIn queries). It also marks the key differentiator from siblings with 'WITHOUT persisting anything' and the title adds '(no save)', so it is unambiguously distinguishable from sdr_create_search.

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?

Includes an explicit workflow directive: 'Use to review/edit before calling `sdr_create_search`.' This names the exact sibling tool to call next and the condition (preview/review before persisting), leaving no inference required about when to invoke this tool versus alternatives.

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