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

Annotations already declare destructiveHint=true and non-idempotent, but the description goes well beyond them: irreversibility ('This cannot be undone'), the referential-integrity refusal conditions (angles using a persona/pillar, posts, answer-engine checks, AI-visibility results), and the fact that the error message names the blockers. This is exactly the extra context annotations cannot convey.

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?

Front-loads the irreversible delete, then the refusal conditions, then the alternative — a sensible priority order with no filler. It is on the longer side and the refusal sentence is densely nested, but each clause carries distinct operational 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 destructive tool with full schema coverage and an output schema (so return values need not be described), this covers everything an agent needs: irreversibility, the failure modes it will hit, the workaround, and the related tools.

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 100%, so both parameters (id, kind with enum) are already documented, including the id source (get_brand_context) and the buyer-question exclusion on kind. The description adds no format or value semantics beyond that, so it sits at the baseline rewarded by a complete schema.

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?

Opens with a specific verb ('Permanently deletes') and enumerates exactly which strategy item kinds are affected (persona, pillar, angle, market, KPI target), immediately carving out buyer questions as non-deletable. An agent can distinguish this from save_strategy_item and the other delete_* siblings without inspecting the schema.

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?

Gives explicit when-to-use and when-not: buyer questions can only be retired via save_strategy_item with active: false, and in-use items must be retired rather than deleted. It even names the remediation path (delete or move the dependent angles) when the refusal fires, leaving nothing to inference.

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