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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so safety is covered; the description adds the genuinely non-obvious disclosure that lead rows are permission-scoped ("the ones this person sees") while stage counts and money are team-wide. That visibility asymmetry is exactly the kind of behavior an agent could otherwise misreport. No mention of result size, pagination, or how deep the stage list is.

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 second sentence is a 40-word run-on stacking field after field (funding, revenue from statements, lender answers, offers, funded this/last month), and the opening "Where the deals stand" is softer than a direct verb. Content is relevant, but the density hurts scannability and the usage sentence is buried at the end rather than front-loaded.

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 return-value burden and does list the relevant payload components, plus it explains the personal-vs-team scoping. For a one-optional-param read tool that is nearly sufficient; only scale/timing questions (how many stages, freshness of "this month") go unanswered.

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% and the schema itself explains the single optional `stage` filter ("its name as the answer gives it"), so the baseline is 3. The description only alludes to stages descriptively and adds no constraint, format, or case-matching guidance beyond 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?

"Where the deals stand: each stage with its leads" plus an enumeration of returned fields (days in stage, owner, next step, funding, offers) makes the resource and its contents unmistakable. It does not name any sibling (get_lead, list_leads_in_list, search_leads) or say how it differs from a single-lead lookup, so differentiation is left to inference.

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 trailing sentence gives concrete triggering queries ("what's in the pipeline", "which deals are stuck"), which is stronger than generic context. There are no exclusions — nothing tells the agent when to prefer get_lead or search_leads instead — but the positive usage signal is clear.

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