agentFeedback

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

With no annotations at all, the description carries the full behavioral burden and does so well: it discloses that recurring feedback auto-promotes into per-session guidance, that the user can pin/edit/veto that guidance, that 'rule' is the field that actually gets promoted, and that high severity lowers the recurrence threshold. It also discloses the default recording scope as device-local diagnostic, which an agent could not infer from the schema alone.

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?

One dense paragraph that front-loads purpose, then field expectations, then the promotion consequence. Every clause does work, though the parenthetical enumerations make it feel packed; a couple of sentences could be tightened without losing 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 9-parameter mutation tool with no annotations, the description covers what an agent must know before calling: required fields, optional-but-encouraged fields, scope default, and the downstream effect on session guidance including user override. Since an output schema exists, the absence of return-value prose is not a gap.

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 100%, so the baseline is 3, but the description adds real meaning on top: it identifies category/severity/summary as the required trio, clarifies 'surface' as part of the recurrence cluster and thus encouraged, and explains that severity's high value triggers promotion at a lower threshold — a consequence the enum alone doesn't convey.

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 opens with a specific verb and resource — 'Record durable feedback about using Mazarbul' — and enumerates the friction categories and the 'lesson' alternative, so the agent knows exactly what belongs here. It falls short of a 5 because it never names the sibling tools it could be confused with (remember, fact, contextPin) to draw the line between logging a rule as feedback versus storing it as knowledge.

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?

It states a clear usage condition ('File DURABLE friction or rules') and an explicit exclusion ('not one-off disagreements'), which is exactly the kind of judgment call an agent needs. What's missing is a pointer to the alternative path for non-durable cases or for facts, so the routing is only half-resolved.

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