get_campaign_leads_stats

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It correctly discloses the critical behavioral trait that offset-based pagination with skip>0 or status filtering fetches all pages client-side, then filters/slices. However, it does not describe the return format (what fields constitute 'per-lead statistics'), auth requirements, error handling, or rate limits. The disclosure is adequate for the main performance implication but leaves significant gaps.

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 only two sentences, front-loaded with the primary purpose in the first sentence. The second sentence packs all pagination details and behavioral nuance without redundancy. Every word earns its place, and there is no fluff.

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 has 6 parameters, no output schema, and no annotations, the description covers purpose, pagination modes, and a key behavioral note. However, it fails to describe the return value structure (what fields are in the 'per-lead statistics' array), which is a significant gap for an agent to correctly process the tool's output. It also does not mention that campaignId is required (though schema covers it) or handle edge cases like empty results. The description is incomplete for a tool of this complexity.

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%, so each parameter already has a description in the schema. The description adds value by grouping parameters into two distinct pagination strategies (cursor-based vs. offset-based) and explaining the behavioral consequence of using offset/status parameters. This context is not present in the individual schema descriptions and enhances the agent's understanding of parameter interactions. It could be clearer about mutual exclusivity between cursor and offset parameters.

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 'Get per-lead statistics for a campaign,' which is a specific verb+resource combination. It distinguishes the tool from siblings like get_campaign_stats (aggregate stats) and get_campaign_leads (likely just leads). However, 'per-lead statistics' is somewhat vague without specifying what statistics are included (e.g., replies, conversions), which prevents a perfect score.

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 explains two pagination modes and warns that offset-based pagination (skip/status) triggers a full client-side fetch, which is a valuable usage constraint. However, it does not explicitly state when to use this tool vs. alternatives (e.g., 'for aggregate stats, use get_campaign_stats'), nor does it provide guidance on when not to use it beyond the pagination trade-off. The guidance is partially present but not comprehensive.

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