memory_maintenance

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

With no annotations provided, the description carries the full behavioral burden, and it does disclose state mutation (backfill, rebuild) plus the potentially destructive 'optionally expire low-value records' path. However, it never mentions the dry_run default of true, the safety consequences of setting expire=true, what qualifies a record as low-value, or whether expiration is reversible.

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?

The description is a single front-loaded sentence with zero filler: the main verb and resource come first, followed by a compact colon-led list of operations. It is efficient, though the brevity sacrifices the safety context that a mutating maintenance tool warrants.

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-value coverage is not required, but annotations are absent and schema parameter coverage is 0%, leaving the description as the sole behavioral source. It fails to explain limit, dry_run and its default, or the destructive consequences of expiration, so an agent cannot safely judge whether running this against production memory is appropriate.

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, but it only maps the concept of 'expire low-value records' to the expire flag. The limit parameter (a processing threshold) and the safety-critical dry_run parameter (which defaults to true) are left entirely unexplained, leaving an agent unable to reason about what a call will do.

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 clearly identifies a specific verb and resource ('Run memory maintenance') and enumerates three concrete operations: backfill meta, rebuild indexes, and optionally expire low-value records. This reads as distinct from the many get/list/add siblings, though it does not explicitly differentiate from similarly maintenance-flavored siblings like memory_episode_consolidate and memory_auto_extract_cleanup.

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?

No guidance is given on when to invoke this tool versus alternatives; the siblings include memory_episode_consolidate and memory_auto_extract_cleanup, which are plausible substitutes for a maintenance task, but no routing information is provided. The only usage signal is the generic phrase 'Run memory maintenance,' which implies intent but states no conditions, prerequisites, or exclusions.

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