Judge one or more pending/watching items

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

No annotations are provided, so the description carries the full burden. It openly declares itself a mutating tool, requires explicit consent, warns of potential housekeeping writes even on read intent, and explains that `drop` never deletes bookmarks or lifecycle records and is fully undoable. It also discloses the `actorClaim` caveat (not proof of consent, cannot be verified, `ai` rejected unless env var set).

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 yet highly efficient. It opens with a bold 'MUTATING TOOL' warning and packs consent requirements, state transitions, side effects, error behavior, and attribution caveats into five purposeful sentences. No filler; every clause contributes critical information.

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 complex mutation tool with no annotations and no output schema, the description covers prerequisites, allowed transitions, error responses, reversal path via `undo`, housekeeping side effects, and consent/attribution limitations. It even points to the README for deeper details, making it fully actionable for an agent.

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?

The input schema has 100% description coverage, so the baseline is high. The description adds behavioral nuance beyond the schema: it clarifies the side effects of `drop`, the 30-day window for `watch`, and the consent limitations of `actorClaim`. While it doesn't restate each parameter, it enriches understanding of how those values operate in context.

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 clearly states the tool's function: it moves items to `kept`, `watching`, or `lapsed` states, and the title specifies 'pending/watching items'. It distinguishes from siblings by defining the state machine explicitly and referencing `undo` as the reversal tool, making the purpose 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?

The description gives explicit when-to-use and when-not-to-use guidance: it must only be called after explicit user confirmation of exact item IDs and action, unless trusted autonomous-approval mode is enabled. It also specifies state-dependent rules (from `pending` all actions allowed, from `watching` only `keep`) and directs readers to `undo` for reversing decisions, clearly separating this tool from alternatives.

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