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

Annotations only say readOnlyHint=false, idempotentHint=false, destructiveHint=false; the description adds the concrete consequences an agent actually needs — one text credit consumed per call, usage logged, and no persistence or publication side effects. That is real behavioral context beyond what the annotations carry, and it is consistent with readOnlyHint=false (credits are spent, usage is recorded).

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?

Core content is front-loaded and dense with useful facts, but the trailing French restatement largely duplicates the English text and adds length without new information for most callers.

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 correctly states the return is text only and that nothing is persisted, which is the key completeness requirement. Minor gap: it does not clarify the role of workspace_uuid relative to the 'content profile' it invokes, though this is not blocking for a 5-parameter generator.

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 60%: tone, prompt, instructions and character_limit are documented in the schema, leaving workspace_uuid unexplained there. The description clarifies that workspace-held instructions/brand voice/account settings feed generation, which adds meaningful context, but it does not explain workspace_uuid itself or how 'instructions' interacts with the stored profile.

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?

Specific verb + resource ('write social media copy with the AI provider') with the scope of what it draws on (workspace instructions, brand voice, account settings). It explicitly distinguishes itself from the sibling create_draft_post by stating that nothing is saved or published and the result must be passed on.

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 clear routing: use this to produce copy, then hand the text to create_draft_post to persist it. It also implicitly excludes the publish/save path by stating this tool does neither, so an agent can pick between generation and drafting without opening the schemas.

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