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

Annotations already declare idempotentHint=true and destructiveHint=true; the description adds value beyond them by spelling out partial-update semantics, the null-clears-connection behavior of socialBrandId, the hosting/connected distinction, and the approval-gated publish workflow. No permissions or error behavior is described, but the destructive and idempotent traits are meaningfully elaborated.

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 information-dense sentences that front-load AND-support, the dual posting modes, then the approval workflow. Every sentence carries operational content; the account-source parentheticals are slightly heavy but justified given the ID-lookup dependency.

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 9-parameter mutation tool with no output schema, the description covers mutation semantics, ID provenance, null-clearing, and the downstream approval gate. Missing only authorization requirements and the managed-vs-connected interaction edge cases, which are minor against what is provided.

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?

With only 33% schema description coverage, the description compensates by explaining the three most ambiguous parameters (managedAccountIds, socialBrandId, socialAccountIds), their sources, the brand-account constraint, and the null-clear semantics. The five personality fields (voice, audience, brandFacts, etc.) are grouped generically rather than individually defined, which is the only notable gap.

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 (Update) and resource (influencer agent) and enumerates the two families of fields it touches: personality fields and posting accounts. An agent knows what is being changed. It stops short of distinguishing itself from close siblings like update_influencer or update_influencer_knowledge, but the scope is unambiguous.

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 real operational guidance ('Pass only what changes') and tells the agent where IDs come from (list_managed_accounts, list_social_brands, list_social_accounts) plus the constraint that social accounts must belong to the brand. It never states when to choose this tool over update_influencer, so the sibling-routing guidance is only implied.

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