pipeline_summary

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the shape of what is computed, which is genuinely useful behavioral context, but says nothing about time window, caching, or scope of the aggregation.

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?

A single front-loaded sentence that lists the three metric groups with no filler. Every clause earns its place.

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?

For a read-only aggregate with no output schema, the description usefully enumerates the returned metrics, but it leaves open the time period, the definition of win rate, and the undocumented state filter. Adequate but with clear gaps.

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?

There is exactly one parameter (state, an enum of Australian states) with 0% schema description coverage, and the description never mentions filtering by state at all. Because a parameter exists, the baseline-4 rule for zero-param tools does not apply, and the description fails to compensate for the coverage gap.

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 names the resource (leads/pipeline) and enumerates the specific aggregates returned: counts by status and source, unassigned open leads, and win rate. That clearly distinguishes it from record-returning siblings like search_leads and get_lead. It lacks an explicit verb, but the resource and output scope are unambiguous.

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?

There is no guidance about when to use this aggregate tool versus siblings such as search_leads or get_lead, and no mention of prerequisites or filters. An agent must infer that this is a reporting/overview call rather than a record lookup.

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