Edit a memory

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, and the description adds real context on top: required scopes (memory:write, luca:draft), full_content data sensitivity, a mandatory Idempotency-Key with server-side generation fallback, and the workspace override behavior. It still doesn't say what is overwritten on a content edit or how a stale write behaves.

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 the one-sentence purpose and its four modes, followed by compact operational lines for path, scopes, idempotency and workspace. The metadata lines are terse rather than padded, though they read slightly like a spec dump.

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?

An output schema exists, so return values need not be described, and the description covers the edit modes, authorization, idempotency and workspace targeting. The remaining gap is the unstated conflict/stale-write semantics of expectedUpdatedAt for what is a destructive mutation.

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 60% and the nested body contains many undocumented fields (expectedUpdatedAt, evidence, metadata, trustLevel, confidence, disputedReason). The prose maps the four modes loosely to boolean/string fields (content, disputed, restore, preferred), which adds some meaning, but it leaves the optimistic-concurrency and provenance parameters unaddressed. Baseline 3 is appropriate.

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+resource ('Correct one memory') and enumerates four distinct edit modes: fixing a fact, flagging disputed, restoring an archived item, and marking preferred over a conflicting memory. It does not, however, disambiguate from the sibling luca_memory_set_archived, which the 'restore an archived one' clause overlaps with.

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?

Gives clear situational context for each mode ('flag it disputed when it turns out to be wrong'), so an agent knows which operation it is selecting. It stops short of any exclusion language or explicit alternative routing (e.g., use luca_memory_set_archived instead), which is the difference between a 4 and a 5.

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