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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description nonetheless adds real behavioral context the annotations can't: it is 'fast' while the alternative 'walks every activity row and may not finish on a large campaign' — a genuine cost/timeout trade-off that shapes tool choice.

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-loads what it returns, then the diagnostic use case, then the performance caveat, then the follow-up tool. Every sentence carries distinct information; the rhetorical quotes and em-dashes are stylistic, not filler.

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 and no annotations gap, the description does need to convey the return shape, and 'counts per step' does that adequately for a 2-parameter read tool. It could be slightly more precise about whether steps are keyed by sequenceId and whether zero-activity steps are included, but nothing essential to correct invocation is missing.

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 both parameters are documented in-schema (campaignId sourced from campaign_list/campaign_create, sequenceId as the step filter). The description adds no further syntax, defaults, or edge cases for either parameter, so it sits at the baseline rather than above it.

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 and resource — pending/completed/failed counts for every step of a campaign — and frames it as 'the funnel view'. That framing plus the explicit contrast with analytics_funnel and sequence_leads_at_step lets an agent separate it from the many campaign/analytics siblings without opening a schema.

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?

Gives a clear selection rule: use this for 'where are we losing people', prefer it over the slower funnel alternative on large campaigns, and switch to sequence_leads_at_step to get the underlying leads. The only defect is that the named alternative `analytics_funnel` does not match the sibling tool `analytics_campaign_funnel`, which could send an agent looking for a tool that isn't there.

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