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

Annotations only declare readOnly/openWorld/non-destructive; the description adds substantial context beyond that — the 14-day horizon, the automatic skipping of already-occupied slots, and the three named empty-list reasons (NOT_ENOUGH_DATA, NO_RELIABLE_SLOTS, ALL_SLOTS_OCCUPIED) with their thresholds (3+ samples). It also guarantees no fabricated times, which is exactly the kind of behavioral contract an agent needs.

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-loaded with the core promise, then progressively adds handoff, return-field decoding, and failure modes. Dense but nearly every clause carries information; the parenthetical slot-hour examples are helpful rather than padding, though the single block paragraph could be broken for scanability.

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?

An output schema exists, yet the description still supplies the interpretive keys an agent needs (slot-hour mapping, dayOfWeek encoding, per-suggestion engagement/sample count) plus empty-result semantics. For a zero-required-parameter suggestion tool, nothing material is left unexplained.

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 100%, so the schema already documents all five parameters including timezone handling for `from` and the platform-vs-platformConnectionId precedence. The description's added detail (dayOfWeek 0=Sunday, slot n = hours [n×4,(n+1)×4)) concerns returned values rather than input semantics, so it adds little on the input side 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?

States a specific verb (suggest) and resource (concrete upcoming posting times) with explicit provenance — the organization's own best-performing slots over the next 14 days. This is clearly distinguishable from analytics siblings like get_analytics_insights or get_top_posts, which report past data rather than propose future publish times.

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?

Explicit downstream routing: 'Pass a suggestion's scheduledAt straight to create_post or reschedule_post', and explicit failure handling ('tell the user rather than guessing'). What is missing is an upfront when-to-use statement versus analytical siblings, but the handoff guidance is concrete and actionable.

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