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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally. The description adds genuinely useful retry guidance ('Reuse idempotencyKey on retry'), which operationalizes the idempotent hint. It does not disclose what data is destroyed (tracked history, scan results) or whether removal is reversible, which would be valuable for a destructive operation.

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 short sentences, zero filler, with the destructive action stated first and the retry guidance second. Every sentence earns its place and nothing is front-loaded poorly.

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?

An output schema exists, so return values need not be described. For a destructive, non-readOnly tool with complete schema-coverage failure on parameters, the description is adequate but thin: it omits the effect of deletion on downstream artifacts and doesn't clarify how a targetId is obtained (list_intelligence_targets / get_intelligence_target).

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 0% across three required parameters, so the description carries the full explanatory burden. It only addresses idempotencyKey (reuse on retry), leaving brandId and targetId entirely undocumented in both schema and description — an agent must infer their meaning from names alone. Partial compensation for a three-parameter gap is insufficient.

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 specific verb and resource: 'Remove the selected tracked public source from this brand.' This clearly distinguishes it from sibling add_intelligence_target and from the unrelated delete_intelligence_saved, without naming those siblings explicitly. 'Selected tracked public source' is slightly indirect for what the schema calls a target, but the intent is unambiguous.

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?

'After the user requests removal' gives an implied trigger condition, suggesting this action should follow explicit user intent rather than autonomous invocation — useful for a destructive tool. However, no alternatives or exclusions are named (e.g., when to use delete_intelligence_saved or get_intelligence_target first to resolve a targetId), so usage is implied rather than spelled out.

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