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

Annotations already cover the safety profile (read-only, idempotent, non-destructive), yet the description adds substantial operational context: paused campaigns are excluded until resumed, LinkedIn invitations count toward queued sends, expected_contacts includes people already in a sequence, drafts_awaiting_decision includes edit-needing drafts, and unreadable segments are reported as unavailable rather than zero. The last point is a genuinely valuable disclosure that prevents the agent from misreading a missing value as a zero forecast.

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?

One front-loaded paragraph that leads with the core action and scope before drilling into counted categories. It is dense and clause-heavy, but nearly every clause carries a distinct fact (exclusions, inclusion rules, unavailable handling) rather than 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, the description carries the burden of explaining return content, and it does: capacity, expected volume, approved queued sends, drafts in review, first messages awaiting batching, plus named fields like expected_contacts and drafts_awaiting_decision. Edge cases (weekend boundary, unavailable segments) are covered, leaving nothing an agent needs before calling.

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 50%: timezone is documented in the schema, but the week enum values are not. The description compensates by defining 'current' as today-to-Sunday, 'next' as Monday-to-Sunday, and clarifying the weekend interpretation of 'this coming week'. It adds little beyond restating the UTC fallback for timezone, but the enum gap is fully closed.

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 (forecasts) and a precisely scoped resource: per-channel outreach send volume for the current or next week. The scope detail (capacity from limits and sending days, queued sends, drafts, Copilot/Autopilot backlog) makes clear this is a forward-looking capacity forecast, which no sibling tool (previewSenderAllocations, getOutreachAnalytics) provides.

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 through the week enum explanation and the weekend rule ('On a weekend, "this coming week" is next'), which tells the agent how to pick a value. However, it never states when to call this versus related tools like previewSenderAllocations or getOutreachAnalytics, nor any precondition for calling it.

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