crm_analyze_activity_patterns

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes the tool as an analysis/BI operation, implying a read-only nature, but does not explicitly state whether it modifies data, requires specific permissions, or has rate limits. The 'Error Recovery' note about insufficient data provides some insight into behavior, but overall the description lacks detail on side effects and operational constraints. This is a moderate gap, not a contradiction.

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 well-structured with clear headings (Prerequisites, Next Steps, Business Value, Error Recovery) and a front-loaded purpose statement. The first sentence is concise and action-oriented. While the 'Business Value' and 'Next Steps' sections are somewhat tangential for invocation purposes, they are brief and do not bloat the description. It earns a 4 for effective organization and economy of language.

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?

The tool has 5 parameters (all schema-described) and no output schema. The description provides useful workflow context (prerequisites, next steps) and error recovery, which helps an agent decide when to use it. However, it does not describe the return format or what the analysis output looks like, which is more critical given the absence of an output schema. It is adequate but leaves a gap in understanding the tool's complete behavior.

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%, so all parameters are documented in the schema. The description adds minimal extra semantics, only alluding to 'different grouping' in the error recovery note, which weakly references the group_by parameter. It does not explain module_name, date formats, or per_page beyond what the schema already states. Thus, the description contributes little beyond the baseline provided by 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 clearly states the tool's function: 'Analyze activity patterns and trends in CRM data - business intelligence for user behavior'. It uses a specific verb (analyze) and resource (CRM activity patterns), distinguishing it from sibling tools like crm_search_by_timeline (which searches timeline events) and crm_analyze_module_permissions (which analyzes permissions). The purpose is unambiguous and differentiates from related 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 description provides explicit workflow context via 'Prerequisites: Use crm_search_by_timeline to identify activity periods' and 'Next Steps: Generate insights reports → Optimize workflows → User performance analysis'. It also includes an error recovery hint: 'If insufficient data, try broader date range or different grouping'. While it doesn't explicitly name alternatives or exclusions, the prerequisite clearly indicates when to use this tool after timeline search, which is sufficient guidance.

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