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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds substantive behavior beyond them: who sees whose rows (owner/admin/reviewer vs manager vs rep with team average), that comparison defaults to the equivalent preceding days, and that a list restricts scope to its leads.

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 core payload — the metric list — is front-loaded, and the visibility and example-usage sentences follow in a logical order. The metric enumeration is long and the sentences are clause-heavy, but each clause conveys distinct information rather than padding.

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 no output schema, the description carries the burden of telling the agent what comes back, and it does so by enumerating the metrics and the per-person/AI-caller/team breakdowns. It also documents the permission-dependent result scope. Remaining gaps are minor, such as timezone or aggregation granularity.

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 three parameters are already documented with enums and defaults. The description adds only light framing — "over a period" for range, "same days before" for compare, and "the leads on it" for list_id — none of which goes meaningfully beyond the schema text.

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 states a specific resource (floor performance over a period) and enumerates the exact metrics returned — dials, connects, conversations, talk time, texts, replies, emails, booked/won/funded. It also names the breakdown dimensions (per person, AI caller, everyone, prior-period comparison), which makes it clearly distinguishable from siblings like get_pipeline or get_ai_caller.

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?

It supplies concrete trigger questions ("how many dials did we make this week", "how am I doing against the team") that map directly onto when to call it, and explains the role-based scoping that determines whether the result is even the right one for the caller. It stops short of naming an alternative tool for when a different aggregation is wanted.

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