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

Annotations already declare destructiveHint=true and idempotentHint=true, so the danger profile is structured. The description earns credit for adding a real consequence beyond those flags: 'Past deltas are no longer readable,' which tells the agent that historical data becomes unavailable, not just that the feed object disappears. It still omits whether deletion is reversible or what happens to in-flight consumers of the feed.

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 with zero filler. The action is front-loaded and the consequence follows immediately, which is exactly the right ordering for a destructive tool.

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 two-parameter destructive tool with full annotation and full schema coverage, the definition covers action and one key consequence. It lacks the remaining pieces an agent would want before an irreversible call: confirmation that deletion cannot be undone, any permission or ownership requirement, and error behavior for a nonexistent feed. Adequate but with identifiable gaps.

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 100% for both slug and feed_id, so the schema already carries the parameter documentation. The description adds no additional semantics such as whether feed_id must belong to the given slug or what format it takes. Baseline 3 is appropriate when the schema does all the work.

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 gives a specific verb+resource: 'Stop a feed and remove it.' An agent knows exactly this is the terminal operation on a feed, distinct from alterlab_feed_list, alterlab_feed_deltas, and alterlab_feed_update by name implication. It stops short of naming which sibling to use instead when the agent only wants to pause rather than delete, so it is clear but not sibling-differentiating at the top level.

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?

There is no explicit when-to-use guidance and no exclusions. The phrase 'Stop a feed' hints at the pause-vs-delete distinction, but the agent is never told that alterlab_feed_update is the non-destructive alternative, nor what prerequisites (ownership, feed existence) apply. Usage must be inferred entirely from the verb.

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