memory_stats

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

Annotations already establish the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add context. It does: it discloses that output includes operational write-path internals (embedding backfill queue, outbox intents, swallowed errors by component over a 24h window, importance budget clamps), which signals both scope and the presence of a time-bounded error view. It stops short of 5 because it doesn't describe return shape or freshness beyond the 24h hint.

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?

A single sentence, front-loaded with the tool's identity ('Memory statistics with health metrics') followed by the coverage list. It is dense but every clause names a distinct returned category, so little is wasted. The long comma-separated enumeration is slightly harder to scan than a structured breakdown would be.

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 zero-parameter, read-only stats tool with no output schema, the enumeration of reported categories effectively substitutes for a return-value description, so an agent knows what to expect. Given the low complexity and annotation coverage, this is largely complete, with the only real gap being routing relative to the sibling report/stats tools.

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?

The tool takes no parameters (0 params) and the schema is an empty object, so there is nothing for the description to disambiguate. The baseline for a zero-parameter tool is 4.

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 gives a specific resource (memory statistics / health metrics) and then enumerates the exact categories reported: sessions, knowledge by type/project, retention zones, stale records, storage size, config, and write-path diagnostics. That enumeration tells an agent what this tool covers far better than the name alone. It does not, however, explicitly distinguish it from closely related siblings such as memory_perf_report or memory_graph_stats, so it stops short of a 5.

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?

There is no statement of when to use this tool versus alternatives, and no mention of the sibling reporting tools (memory_perf_report, memory_graph_stats, memory_report) that overlap with it. An agent must infer the appropriate context from the name and content list alone.

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