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

Annotations only declare it is a safe read; the description goes well beyond that by defining the inclusion rule (wins require confirmed attribution and no status conflict) and a material data-quality caveat — that nonzero coverage.unresolved_deals or won_deals_missing_amount means revenue is a lower bound rather than an exact figure. That is exactly the kind of trust/interpretation context an agent cannot get from annotations.

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?

Three sentences, front-loaded with the return payload before the qualification rules. The metric list is dense but each item is a distinct field the caller gets, and the two caveat sentences are short and load-bearing.

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 present, the description takes on responsibility for describing the return shape and does so by naming the metric groups and even the nested coverage fields. Combined with the read-only annotations and the workspace-vs-ICP scoping, an agent has enough to call and interpret it correctly.

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 0%, so the description carries the burden, and it does explain the meaning of the single nested parameter: omit to get workspace-wide figures, supply an ICP to restrict to one. It never names icp_id or notes its UUID form, so the mapping is inferable but not explicit.

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?

"Returns won-deal insights" names a specific verb and resource, then enumerates the actual contents (repeat-customer rate, lifetime and repeat revenue by currency, coverage, industry/size/country/ICP segments) and the scope (workspace or one ICP). An agent can tell this apart from pipeline/deal-summary siblings purely from this text.

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 scoping choice is stated (whole workspace, or narrow to one ICP), which implies when to reach for it, but there is no explicit "use this instead of getDealSummaries / getPipeline / getOutreachAnalytics" routing despite many overlapping siblings. Exclusions and preconditions are left to inference.

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