cleanup_suggest

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description goes well beyond by stating it is additive (nothing moved, closed, or deleted), that approvals apply only one suggestion, are reversible via history, and that rejected suggestions are not re-surfaced. That is rich behavioral context an agent cannot get from the annotations.

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 purpose and the non-destructive guarantee are front-loaded, and every sentence carries information (write semantics, approval model, kind defaults). It is a dense single block, but there is little waste; tightening the parentheticals would help readability.

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?

With no output schema, the description must convey outcomes, and it does — suggestions enter a review queue, user decisions are per-suggestion, and effects are undoable. It does not mention volume, pagination, or how many suggestions are produced, a minor gap for a generator tool.

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 67%. The description adds value the schema lacks: the default that kinds covers all three values, and confirmation that project is required for the write even though the schema marks no required params. It leaves 'model' unaddressed, but that param is already documented in the schema.

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 — find duplicates/stale/misfiled records and place them in the review queue as suggestions — and clearly distinguishes itself from siblings like review_list and review_approve. An agent can tell exactly what this produces without opening the 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?

Explains the workflow context well: this only generates suggestions, the user approves/rejects each, and rejected suggestions are not repeated. However, it never names the alternative tools (review_list, review_approve, todo) to route the agent, so it falls short of explicit when-vs-which guidance.

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