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

Annotations already declare readOnly/idempotent, so the description is free to disclose the behavior that matters: result ordering (newest first), the pagination contract ('pass next_cursor as cursor'), how from/to filter semantics differ by input type, and the filter-combination rule. These are behavioral facts the agent cannot infer from the schema or annotations.

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?

Three dense sentences with zero filler; the retrieval shape and pagination come first, then filters, then the caveat about undated drafts. Each clause carries information an agent needs to call the tool correctly.

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 10 parameters, an output schema, and strong annotations, the description covers the pieces that structured fields cannot: ordering, pagination loop, filter conjunction, and the undated-drafts edge case. Nothing needed to call it correctly 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 80%, so the baseline is 3, but the description adds genuine meaning: channel_id targets one account while group_id targets any account in a group, query searches caption or internal label, and date-only vs offset timestamps filter different units. The inclusive-UTC-day rule is stated only in the description, not the schema, making it a load-bearing addition.

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?

Opens with a specific verb+resource+scope ('Posts in a workspace, newest first, with cursor pagination'), so the agent knows exactly what it retrieves and in what order. It does not explicitly differentiate from siblings such as get_post or list_channels, leaving the single-vs-many distinction implicit.

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?

States that filters combine and gives a concrete usage rule for the edge case: 'Posts without a date (unscheduled drafts) only appear without from/to.' That is real when-to-use guidance. It stops short of naming alternatives (e.g. get_post for a single record) or exclusion conditions beyond the draft case.

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