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

Goes beyond annotations by disclosing non-obvious side effects: invalidating cached scores and rescheduling scoring variant generation. This is valuable behavioral context that an agent needs to anticipate consequences, and it does not contradict the idempotent or non-destructive hints.

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 tightly-scoped sentences: the operation, the update semantics, the side-effect warning, and a pointer to the prerequisite lookup tool. No filler, front-loaded purpose, every sentence earns its place.

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 moderate-complexity update tool, the description covers purpose, patch semantics, side effects, and ID discovery. A minor gap is that it does not clarify whether supplying an array field replaces the entire list or merges with existing values, and there is no mention of error conditions or return values, though no output schema exists.

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?

With 0% schema description coverage, the description compensates by explaining the essential patch behavior: supplied fields change, omitted fields remain unchanged. It also tells the agent how to obtain the required icpId. Individual field names like titles, keywords, and industries are largely self-explanatory, so the lack of per-field detail is acceptable.

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 states a precise operation: 'Update an existing ICP's criteria.' The verb 'Update' and resource 'existing ICP' make it unmistakable and clearly distinguish it from sibling tools like campaignstack_create_icp and campaignstack_delete_icp.

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?

Explicitly instructs partial-update semantics ('Only supply the fields you want to change; omitted fields are left unchanged') and points to campaignstack_list_icps for finding ICP IDs. It does not explicitly state when not to use this tool versus create_icp, though 'existing' implies that distinction.

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