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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which establishes the safety profile. The description does not contradict these and adds minimal behavioral context (e.g., that it aggregates over 'matched memories'). It does not specify behavior like handling of empty results or the exact output format, but with an output schema present, the bar is lowered. This is an adequate but not enriching disclosure.

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 short sentence, which is concise and front-loaded with the main verb. However, it is so terse that it omits essential specificity (e.g., metric options, relationship to siblings). It is not verbose, but it is under-specified, which is a structural weakness.

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?

Given the tool's medium complexity (3 params, output schema) and the large sibling set, the description fails to provide necessary context. It does not explain the metric enumeration, the role of the query parameter, or how this differs from memory.count/stats. The presence of an output schema reduces the need to describe return values, but the description still lacks enough to guide correct selection and invocation.

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 100% (all three parameters have descriptions), so the baseline is 3. However, the description's phrase 'numeric or categorical field' is misleading because the metric parameter is an enum of aggregate types, not a field name. This actively confuses interpretation rather than adding value. The description does not clarify the meaning of 'metric' or the limit default, relying solely on schema.

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 states a clear verb ('Aggregate') and resource ('memories'), and mentions 'numeric or categorical field' which hints at the metric parameter. However, it is vague about what specific aggregates are available (the metric values are count, session_count, session_span) and it uses the word 'field' when there is no such parameter. It does not differentiate from siblings like memory.count or memory.stats, leaving the agent to infer exact behavior.

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 explicit guidance is given about when to use this tool versus the many siblings (e.g., memory.count, memory.stats, memory.list). The description does not mention alternatives, usage contexts, or prerequisites. With a crowded toolset, this is a significant gap.

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