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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds substantial context beyond them: what is preserved (identity, historical metrics, frozen Scan snapshots), what does not happen (no publication or Scan launch), and a partial-failure repair path via list_competitors/update_competitor that avoids duplicate adds.

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?

Long but dense with zero filler; the core removal behavior and preservation guarantee are front-loaded. Some sentences are heavy (the repair-workflow sentence) but each conveys a distinct operational fact, so nothing egregious 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?

Given an output schema exists, the return explanation is optional, yet the tool still notes it returns the saved item (null on remove) and working scanConfig. Combined with the identifier, precondition, and repair guidance, an agent has everything needed to call it 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 coverage is 100%, so the baseline is 3. The description still adds meaning the schema does not: the oneOf XOR requirement is explained in prose ('requires exactly one configured identity or legacy row ID'), and competitorId is characterized as a compatibility id or saved row id for incomplete-identity repair, clarifying when each identifier applies.

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?

States a specific verb+resource (remove configured roster membership) and immediately qualifies scope by naming what is preserved. It distinguishes itself from add_competitor, update_competitor, and update_topic by naming those siblings and the conditions that route to them.

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 states the input constraint (exactly one configured identity or legacy row ID), failure semantics (missing targets fail; repeat removal is not success), and the precondition/alternative (clear or change a Topic focal entity with update_topic first). This is close to a complete when/when-not guide.

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