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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds genuinely new behavior: it is a soft delete, the generated file and config are removed, restoration is possible, and the confirm gate produces a specific error instead of silently proceeding. It also states the exact return payload {feedId, action:'delete', status:'deleted'}.

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?

Purpose is front-loaded, followed by usage scope, then the DESTRUCTIVE warning with the confirm mechanism, then the return shape and parameter provenance. Every clause contributes information and there is no filler.

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 three-parameter tool with no output schema and zero schema coverage, the description supplies the safety requirement, the failure mode, the reversibility, the return shape, and the origin of each parameter. An agent can call it correctly and safely from this text alone.

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 0%, so the description carries the full burden and does: feed_id is sourced from list_feeds, project_id is called out as OPTIONAL, and confirm must be true or the call fails with 'confirm_required' (HTTP 400) and deletes nothing. That is more than the bare boolean schema conveys.

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 and resource ('Delete a feed') and immediately qualifies the semantics as a soft delete whose file and config are removed but restorable. That distinguishes it from siblings like restore_feed and pause_feed without the agent needing to open a 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?

Explicitly scopes invocation to cases where 'the user explicitly asks to delete a feed' and names restore_feed as the recovery path, which implicitly frames the alternative. It stops short of stating when NOT to use it (e.g., temporary suppression should use pause_feed), so it is clear but not exhaustive.

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