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

With no annotations, the description itself must disclose behavior. It usefully notes that 'credit balance is null until that subsystem ships' and scopes queue depth to today, but it does not state auth requirements, return shape, or whether results are approximate, leaving some burden unmet.

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 front-loaded sentence delivers the core capability then the important caveat, with no filler. Every clause earns its place.

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 low-complexity tool with one optional parameter and no output schema, the description tells the agent what counts it will get and flags a known null field. The only notable omission is a more precise statement of the return format, but the listed counts largely cover it.

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 coverage is 100% and the single optional owner_key parameter is already documented in the schema. 'For your org' lightly reinforces that the parameter scopes results, but the description adds no new parameter-level meaning 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 names a specific verb and resource ('Get counts for your org') and enumerates exactly what is included (KV item count, queue depth today). This distinguishes it from sibling tools like kv_list and queue_list_names, which inspect individual items rather than org-wide aggregates.

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 context for use is clear: use it when you need org-level aggregate counts. However, it never explicitly says when to avoid it or names alternatives, so an agent must infer that kv_list or queue_list_names are the more detailed alternatives.

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