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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=false, so the safety profile is largely covered. The description still adds real value by stating that the result is immediately published and that a retry with the same idempotencyKey and input replays the first result rather than repeating the action. It stops short of explaining the destructive side (what an existing ICP or version loses when superseded).

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 sentences, no filler, and the primary effect (saves targeting as a published ICP) is front-loaded before the conditional versioning mode and the idempotency note. Every clause carries distinct information.

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 tool with a deeply nested audience object, no output schema, and a destructive publish-on-write semantic, the description covers purpose and the versioning switch but leaves return shape, conflict/error behavior, and the audience sub-structure unexplained. Adequate, but an agent would need to open the schema and guess at failure modes.

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%, so the baseline is 3. The description does add meaning the schema does not: it explains that profile_id and expected_version_id together switch the operation from creating an ICP to appending a new version, and it names company_fit and buyer_groups as the payload's substance. It says nothing about the schema_version const, buyer-group roles, or contact_methods, so it only partially compensates for the coverage gap.

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 (Saves) plus a specific resource (Lead engine targeting as a published ICP) and even disambiguates the two creation modes (new ICP vs. new version). It does not, however, distinguish itself from siblings like createIcp, createManualIcp, createIcpDraft, or publishIcp, which an agent could easily confuse with it.

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?

It gives one clear conditional: supply profile_id and expected_version_id to create a new published version of an existing ICP. That tells the agent how to select between the tool's two behaviors, but there is no guidance on when to choose this tool over the many sibling ICP-creation and publishing tools, and no preconditions (e.g., permissions or version-conflict handling) are stated.

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