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

Beyond annotations, the description discloses two behaviors an agent could not infer: the saved item enters a pending state awaiting owner review unless auto-keep is on, and the call requires the 'save memories' permission. That is meaningful added context for a mutation tool with openWorldHint=true, though it does not say what happens on permission failure or whether the pending item is retrievable.

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?

Three short sentences with the core action front-loaded and no filler. The trailing 'when the owner asks' clause in sentence one slightly muddles the ordering of the main action and its condition.

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 explained, and the pending-review workflow plus permission requirement are covered. What remains missing for a 3-parameter mutation tool is the meaning of source_label and any note on duplicate/idempotent behavior beyond the raw hint.

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 only 33% — clone_id is documented in the schema but text and source_label are not. The description's 'note, decision or fact' hints at the content of text but adds nothing about source_label or size/format expectations, so it fails to compensate for the coverage gap.

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 names a specific verb and resource ('Save a note, decision or fact into the owner's consciousness'), making the effect unmistakable and distinguishing it from siblings like list_pending_memories and review_pending_memory. It stops short of explicitly naming the complementary review tool an agent would pair it 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?

'when the owner asks' gives a real trigger condition, and the review/auto-keep note implies when this tool's output becomes visible. However, no alternative is named and no when-not guidance is given, even though review_pending_memory and consult_mind are obvious candidates for confusion.

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