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

Annotations already indicate destructiveHint=true, but the description adds essential context: 'Mutates external platforms when delete_remote is set' and 'already-gone counts as success' (idempotence). It also discloses return behavior ('per-id result map') and clarifies that local campaigns are kept. These details go beyond annotations and are crucial for safe invocation.

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?

The description is dense and mostly front-loaded, with the core action first. However, 'Mutates external platforms when delete_remote is set' is somewhat redundant with the earlier sentence about delete_remote. Still, every sentence carries useful information, and there is no fluff beyond minor repetition.

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 no output schema, the description compensates by stating the return format ('per-id result map') and idempotent behavior. It covers purpose, mutation risk, space scoping, and a follow-up action (trigger_sync). This is exceptionally complete for a destructive tool with no output schema.

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?

Since schema coverage is 100%, the baseline is 3. The description enriches the semantics of delete_remote by noting 'already-gone counts as success', and clarifies space_id as an override for the active Space. While the schema already documents each parameter well, these behavioral details provide additional nuance, justifying a slight bump.

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 opens with a clear specific action: 'Clear a platform link from the active Space's campaigns, keeping the local campaigns.' This distinguishes it from delete_campaign (which removes campaigns entirely) and other sibling tools. The scope is explicit (active Space, per-campaign), and the verb 'unlink' matches the tool name.

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?

The description gives a concrete workflow: 'Unlink then trigger_sync to re-create campaigns cleanly on the platform.' It also explains space-scoping behavior with set_active_space and space_id override. However, it doesn't explicitly contrast with delete_campaign or mention when not to use, but the context is clear enough for an agent to select appropriately.

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