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

There are no annotations at all, so the description carries the full burden of behavioral disclosure. It explicitly states 'Read-only,' which is valuable side-effect information, and clarifies the kinds of counts returned. It does not define 'stale,' but for a simple no-parameter stats endpoint the added transparency is sufficient.

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 extremely compact: one sentence containing the key metrics and a read-only warning. Every phrase adds information, and the most distinctive output ('Counts per stage') is front-loaded.

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, the description covers the essential context: what the tool counts and that it has no side effects. It does not define the 'stale' threshold or timezone semantics, but these are minor gaps for such a simple tool and no output schema exists to provide more structure.

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 input schema has zero parameters, so there is nothing for the description to document. The baseline of 4 applies here because no parameter semantics are needed and the description correctly focuses on the tool's output rather than nonexistent inputs.

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 the resource ('CRM pipeline stats') and specifies exactly what it produces: counts per stage, new leads today/this week, and stale leads. This is specific enough to distinguish crm_stats from crm_list_leads, crm_list_stages, and other CRM listing tools.

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 read-only, aggregate nature of the tool makes its intended use reasonably clear: get pipeline summary counts rather than individual lead details. However, it does not explicitly state when to prefer this over sibling tools like crm_list_leads or crm_list_stages, nor does it mention any exclusions.

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