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

Annotations already cover the safety profile (readOnlyHint, non-destructive, closed-world), so the description earns credit for adding real behavioral detail beyond them: 'group_by' injects a 'groups' block, 'stage' additionally produces a 'funnel' with conversion, and 'period' restricts groups to leads entering in that window. It stops short of describing response size, empty-result behavior, or what «N/200» means in practice.

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?

Front-loaded with the core purpose and tightly compressed — nearly every clause carries parameter or output meaning. The density slightly hurts scannability: heavy use of guillemets and inline parentheticals makes the 'group_by' and 'period' semantics harder to parse than a short bulleted breakdown would.

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 correctly takes responsibility for sketching the response shape (totals, status/source breakdowns, per-day series, goals, groups, funnel) and the parameter interactions that change it. What remains thin is edge behavior: workspace scoping requirements, handling of unknown group_by fields, and result size.

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 0% and there are no enums, so the description carries the full burden — and it largely does: 'days' (default 30), 'period' values including YYYY-MM format and the inbound-vs-created nuance, 'group_by' accepted values (stage, category, custom.<field>, city, week), and 'pipeline' as the source of category/funnel. The circular-sounding defaults ('default the workspace's, else «inbound»') and the unexplained «N/200» notation leave some ambiguity.

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?

States a specific verb+resource+scope: 'CRM lead analytics of the active workspace (read-only)' and enumerates exactly what it returns (totals, by status, by source, per-day new leads, pipeline goals). The 'analytics/summary' framing distinguishes it from listing tools like list_leads or search_leads, though no sibling is named explicitly.

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?

Usage is implied rather than stated: the 'read-only summary' framing plus defaults ('days' default 30, 'period' default all) tell the agent what it will get by default, but there is no explicit 'use this instead of list_leads/search_leads when you want aggregates' guidance or any exclusion.

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