confirm_memory

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

With no annotations, the description carries the burden and does real work: it discloses that a 'contradicted' verdict is non-destructive, halts promotion, and escalates to a human reviewer, plus that feedback is deduplicated ('counted once per person'). It omits the converse behavior (what 'confirmed' actually triggers) and any auth or rate-limit context.

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?

Four short lines, front-loaded with the action and its precondition, then the consequential behavior. The formatting of `verdict` values mid-paragraph is slightly awkward but nothing is padded or redundant.

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 three-parameter mutation-style tool with zero annotation coverage and no output schema, the description covers consequences unusually well but leaves the agent guessing about `node_id` provenance, what `reason` is for, and what a successful call returns. It is adequate to call safely but not fully self-contained.

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 only partly does. It pins the two legal values of `verdict` even though the schema declares no enum, which is valuable, but `node_id` and the optional `reason` are never explained (what belongs in a reason, whether it is shown to the human reviewer).

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 first sentence names a concrete action (reporting a verdict) on a concrete resource (a memory node) and adds a real scope constraint (only nodes actually used this session). It doesn't explicitly name a sibling, but the 'I used this' framing separates it from fetch_nodes and report_gaps by implication.

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?

The clause 'a memory node you actually USED this session' is a genuine precondition that tells the agent when this tool is appropriate and implicitly excludes nodes merely read about or never touched. No alternative tool is named for the other cases (e.g., reporting a bad note you never used), so it stops short of full routing guidance.

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