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

Goes well beyond the annotations (destructiveHint=true, idempotentHint=false) by disclosing exactly what applying does: replaces inferred strategy fields, preserves offer/site/preferences and existing content, and does not regenerate memory. The preview-vs-apply distinction is precisely the mutation semantics 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?

Four dense sentences, each carrying distinct information (scope, precondition, preview/apply rule, preservation guarantees, exclusion). Front-loaded with the action and heavily front-weighted toward the highest-stakes semantics.

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 explains what a call returns (a preview vs an applied change) and what state is preserved. It is nearly complete for a destructive, non-idempotent mutation, lacking only any note about brandId's role.

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 only 33%, but the description compensates for the two most consequential parameters: the apply flag's preview/commit behavior and confirm's AI-usage authorization. brandId is left undocumented in both description and schema, which is the only 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 (infer/refresh) and named resource fields (positioning, audience, pillars, insights) plus the data source (connected social profiles). The closing sentence distinguishes it from the manual per-field editing path (update_strategy_brief), so an agent can tell the two apart without opening schemas.

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 a clear precondition ('Requires confirmed AI usage') and a mode-selection rule ('Returns a preview unless apply true'). It implies when to use it, but never explicitly names update_strategy_brief as the alternative for manual edits — it only negates that behavior.

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