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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, covering the safety profile. The description adds that a new ICP is created and made available for later scoring, but it does not disclose return values or duplicate-creation behavior—modest gaps given existing annotation coverage.

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?

The description is four short, logically ordered sentences: what the tool does, the criteria it accepts, the recommended follow-up action, and how to obtain a required value. Every sentence earns its place, with no filler or unnecessary repetition.

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 6-parameter creation tool with no output schema, the description covers all parameters at a useful summary level and names the follow-up scoring tool. It omits edge details such as whether at least one criterion is required or what the response looks like, but an agent has enough context to select and invoke the tool 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%, so the description carries the burden. It enumerates the five optional criteria parameters and connects campaignId to the campaign concept, even telling the agent how to source valid campaignId values. It does not define value conventions for individual criteria, but the parameter names are largely self-explanatory.

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 clearly states the verb ('Create') and resource ('new ICP (Ideal Customer Profile)') and lists the concrete target dimensions: titles, industries, seniorities, company sizes, and keywords. It is distinguishable from get/list tools, though it does not explicitly contrast with the sibling create_persona or update_icp tools.

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 gives explicit workflow guidance: after creating the ICP, use campaignstack_trigger_icp_scoring to score leads against it, and use campaignstack_list_campaigns to find valid campaignId values. It does not spell out when-not-to-use or name alternatives like create_persona, but the sequencing context is concrete and useful.

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