memory_regulation_preview

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

With no annotations, the description carries the full burden of behavioral disclosure and delivers thoroughly: 'without mutation,' 'dry-run only,' 'will not transport authenticated receipts or mutate Memory,' and the interpretive caveat that empirical_success_floor_ppm is 'a conservative evidence floor, not a held-out task-success claim.' This safety profile and guardrail against misreading the metric is precisely what an agent needs before invoking.

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 core purpose is front-loaded in the opening sentence, and every subsequent sentence adds information: the dry-run authority requirement, JSON array format, evidence-floor interpretation, and the receipts/mutation limitation. There is minor redundancy between 'without mutation' and 'will not ... mutate Memory,' and the dense single paragraph is technical, but at roughly 110 words for an 8-parameter tool, nothing is wasted.

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?

The output schema relieves the description of explaining return values, and the non-mutation behavior is thoroughly disclosed. However, with no annotations and 0% schema coverage, the description leaves five of eight parameters and the decision between empirical_success_floor_ppm versus held_out_task_evaluation_json underspecified for a tool of this complexity.

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. It does for three difficult parameters: categories_json (may be a JSON array; empty array selects no categories), empirical_success_floor_ppm (semantics plus conservative-floor caveat), and held_out_task_evaluation_json (promotion-grade alternative pathway). However, five of the eight parameters — budget, project_id, empirical_success_min_samples, empirical_success_lookback_days, and optimize_for_least_active_memory — receive no semantic explanation in either the schema or the description.

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 states a specific verb and resource: 'Preview bounded, success-evidence-aware compaction without mutation.' This identifies a dry-run preview of memory compaction, which no sibling tool (memory_regulation_storage_status, memory_store, memory_recall, memory_search) offers. The scope qualifiers (bounded, success-evidence-aware, without mutation) make the tool's role unambiguous.

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 description provides clear usage context: this surface is 'deliberately dry-run only,' and actual compaction requires 'a caller-owned idempotency authority through the SDK or governed operating loop.' An agent learns when the preview is appropriate and that it cannot substitute for real compaction. It stops short of naming sibling MCP tools or stating an explicit when-not-to-use condition, so it does not reach the top tier.

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