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

Annotations already flag mutation, destructiveness and idempotency, and the description adds genuinely useful behavioral context: approval invalidation, platform-specific length checks, skipped unsupported targets, field omissions for status/scheduledTime/mediaUrls, and safe idempotent retry. There is no contradiction with the 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?

The description is dense but front-loaded: it starts with the core action and ordering constraint, then covers special cases and retry behavior. A few sentences duplicate schema-level details, but nearly all content is useful for correct invocation.

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 complex mutation with nested platform settings and no output schema, the definition covers prerequisites, side effects, workflow ordering, verification via company_get_post, media upload alternatives, and idempotent retry. An agent has enough context to call it correctly.

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 already 75% and the nested schema carries substantial field documentation, but the description adds operational meaning: copy channel keys from company_list_channels, empty platforms allows a channel-less draft, firstComment accepts only one object and null clears it, and retries must reuse idempotencyKey. It does not exhaustively explain every nested platform setting, so 4 is appropriate.

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 ('Update an existing Agency draft') and immediately distinguishes it from adjacent workflows by naming company_schedule_post, company_get_post, company_reserve_media and company_complete_media. An agent can identify exactly which operation this is without opening the 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?

Explicitly says to save edits before media, client review or scheduling, notes that changed text/channels/settings invalidate approval, explains the empty-platforms case, and directs scheduling/media operations to the appropriate sibling tools. It also gives retry guidance for a lost response. This is close to ideal when-to-use/when-not-to-use guidance.

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