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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the record is saved as an unpublished draft (implying a separate publish step via publishIcp), and a retry with the same idempotencyKey returns the first result rather than duplicating. It does not mention validation-failure behavior or any permission requirements, which keeps it from a 5.

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 sentences, front-loaded with the when-to-use trigger followed by what is created and the retry contract. The idempotency sentence partly restates the idempotentHint annotation, but it adds the concrete "returns the first result" behavior, so little is wasted.

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 two-parameter but heavily nested write tool with no output schema, the description covers purpose, draft state and retry semantics adequately. It omits the two things an agent most needs: how this differs from createIcp/createIcpDraft/createIcpFromScan, and what a successful call returns (an id? the full ICP?) given there is no output schema.

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 50% and the schema itself is deeply nested, so the description does real work by naming the definition blocks the body must contain. However, it says nothing about body.name, the source enum (manual vs current_form), or the required/optional status of sub-objects, leaving the agent dependent on the schema for the rest.

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?

"Creates a new ICP from a full profile" is a specific verb plus resource, and the enumerated sections (product context, company fit, buyer groups, problems, signals, outreach guidance) tell the agent exactly what payload shape is expected. It stops short of distinguishing this from the many closely related siblings such as createIcp, createIcpDraft and createIcpFromScan, which is the main ambiguity an agent would face.

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 opening sentence gives a concrete trigger: the user describes who they sell to and wants it persisted as an ICP. That is clear usage context, but there are no exclusions or pointers to alternatives, and with three near-identical ICP-creation siblings the agent is left to guess which one applies when the input is not a full profile.

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