sumo_qa_capture_review_feedback

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

Annotations already declare the safety profile (readOnlyHint=false, openWorldHint=false, idempotentHint=false, destructiveHint=false), and the description adds genuinely non-structured behavior: no auto-capture, mandatory user confirmation per write, and a rejection policy for raw diffs, secrets, code and pasted issue/PR bodies. The only tension is that a 'delete' action is offered while destructiveHint=false; that is a mild inconsistency worth noting but the description itself supplies the operational detail the annotation lacks.

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 is front-loaded in one sentence, followed by a compact action/parameter map and then the confirmation and rejection rules. Dense backtick notation is efficient, though the action block is close to schema restatement and the line-wrapped formatting slightly hurts scannability.

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 four-parameter mutation tool with no output schema and no annotation nuance, the description covers actions, scope resolution, nested entry fields and write preconditions well enough to call it correctly. The one remaining gap is that it never says what `list` returns (e.g. whether entries carry the `entry_id` needed for update/delete), leaving an agent to infer the lookup flow.

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% and `entry` is an opaque anyOf object with additionalProperties:true, so the description carries the full burden — and it does, naming the entry fields (`scope`, `trigger_signal`, `recommended_probe`, `source_note`, optional `last_reviewed`) and stating which parameters each action needs. It also documents scope's enum-like values and its error behavior ('else an error') plus the requirement that `entry` carries its own scope. Only field-level types are left implicit.

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 opening sentence states a specific verb and resource — managing a user-confirmed memory of recurring review lessons — and immediately qualifies it as 'advisory hints that never override the catalogues', which separates it from the catalogue/rule loader siblings. The action enumeration ('list'/'capture'/'update'/'delete') makes the CRUD surface explicit 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?

Each action is tied to its required inputs, defaults are named ('list' is default, 'project' is default scope), and the description states that writes require explicit user confirmation and that nothing is auto-captured — a real usage constraint. It does not say when to prefer this tool over catalogue-loading siblings or when capturing feedback is warranted versus simply recording a mutation, so it stops short of full when/when-not guidance.

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