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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds that it does not return content, which is useful. However, it does not disclose what exactly the count represents (e.g., all memory types?) or any performance considerations or limits.

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?

One concise sentence that front-loads the key behavior ('Count memories') and adds the critical side effect ('without returning content'). Zero waste.

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?

With an output schema (likely a count value) and full parameter coverage, the description is largely complete. It could mention whether the count is approximate or exact, but the presence of an output schema and simple parameter list makes it sufficient.

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 schema covers 100% of the parameter (galaxy) with a clear description, so the baseline is 3. The description mentions 'matching optional filters' which implies the galaxy parameter is a filter, but it doesn't add new details beyond the 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 uses the specific verb 'Count' with resource 'memories' and clearly states that it returns a count, not content. This distinguishes it from sibling tools like memory.read, memory.query, and memory.list, which would return actual memories.

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 implies the tool is for counting memories without returning content, which suggests it for aggregation or existence checks. However, it does not explicitly state when to use it over memory.stats or memory.aggregate, nor does it mention any exclusions or alternatives.

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