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

Annotations only declare readOnlyHint=true, so the description does add real value: the unverified-claim warning (don't relay to third parties), the current-vs-superseded default, and the 'filter, not access control' distinction between belongs_to and visibility. However, the schema already carries most of these operational semantics verbatim, so the description's marginal disclosure beyond structured fields is moderate rather than exceptional.

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 return shape and current-state-first ordering, then moves to usage and filtering guidance. It is information-dense and mostly earns its length, though the deep dive into return structure and parameter behavior overlaps heavily with the schema, keeping it from being maximally tight.

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?

No output schema exists, so the description appropriately spells out the return shape ({current, days, belongs_to_options, total, note}) and the fields on each entry. For an 8-parameter, zero-required tool with cross-source aggregation and filtering nuances, nothing essential to correct invocation is missing.

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?

With 100% schema description coverage, the baseline is 3, and the schema already documents each parameter's meaning, defaults, and interactions (tags reliability, belongs_to as filter, include_unfiled/with-belongs_to behavior). The description largely restates this guidance (tags most reliable, combine belongs_to with tags, include_superseded never for current state), adding familiarity and prioritization but little new semantic content.

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 and resource — reads the user's cross-assistant journal — and enumerates exactly what it returns (current.decisions, current.profile, days). It cleanly distinguishes itself from siblings like search_memory (narrow search) and add_memory (corrections via supersedes). An agent can tell what this tool retrieves 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?

Explicitly states when to call it: BEFORE answering questions about current state, when the user asks what happened on other devices/assistants, or at session start — even giving the trigger phrases. It also routes to alternatives by explaining how to narrow with kinds/tags/sources and how to record corrections with add_memory supersedes.

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