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

Despite annotations covering the safety profile (readOnlyHint=false, destructiveHint=false), the description adds substantial context: credit costs per mode, that nothing is saved or posted, and what each mode produces. It clearly discloses the side-effect boundary ('the result comes back to the user to accept or ignore').

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?

Front-loads purpose, then modes, then usage and cost, so it is well-ordered. It is on the dense side, and the opening clause about the 'Improve panel in Content Studio' is marketing framing that does little for agent decision-making, keeping it from a 5.

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 compensates by describing return values ('the improved post with what changed and why', '2 to 3 alternative rewrites'). For a non-destructive, credit-metered tool it covers mutation boundary, cost, and output shape completely.

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 description coverage is 100%, so the baseline is 3. The description earns above the baseline by unpacking the 'full' mode as an ordered pipeline (grammar, opening line, line breaks, platform formatting), which adds meaning beyond the schema's terser mode definition.

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+resource ('Improve a draft') and elaborates with named modes ('full' vs 'quick') plus the internal engine it uses. An agent immediately understands the operation. It does not explicitly name or distinguish itself from adjacent siblings like suggest_hooks or score_voice_match, so it falls just short of a 5.

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 triggering conditions ('Use when the user asks to improve, tighten or fix a specific draft') and a constraint ('once per text', 'for text the user asked to improve'). It also surfaces the credit cost (quick 3, full 5) to inform selection. It stops short of naming alternative tools for the adjacent tasks.

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