optimize_stage

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

With no annotations, the description carries the full burden and does so richly: it discloses that nothing is applied, that the dashboard backs up before the first apply and can undo, that destructive kinds require a non-empty `verified`, that invalid suggestions are skipped and reported in `errors`, and that an over-long `note` raises and stages nothing. This is exactly the mutation/safety context an agent needs.

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?

Front-loaded with purpose and workflow position, then the suggestion contract, then failure modes. The kind enumeration is long but each entry carries unique information the schema does not, so little is wasted; density is high but justified.

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 mutation tool with no annotations and no output schema, the description still supplies the return shape ({run_id, staged, errors}), the skip-and-report error semantics, the destructive-verification requirement, and a pointer to help(command='optimize_stage') for deeper kind documentation. Nothing an agent needs to call it correctly is missing.

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 0%, so the description must compensate and it does: it fully documents the shape of each suggestion (kind, target_uid, payload, rationale, verified), enumerates every kind with its payload fields, explains target_uid derivation for link/merge/distill, and gives `note`'s 250-character cap and raise behavior.

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 — staging curation suggestions for human review — and immediately positions itself as 'Step 2 of the "optimize my memories" workflow', which separates it from the scan/apply siblings. An agent knows this stages rather than applies 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?

Clearly states the context (step 2 of the optimize workflow) and an explicit when-not: 'NOT applied here: the user reviews and applies or rejects each one in the admin dashboard.' It does not name the specific sibling to run first (e.g. optimize_scan), leaving sequencing to inference, so it stops short of a 5.

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