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

Beyond the annotations (destructive, non-idempotent, open world), it discloses that the previous digest is replaced, that the call consumes one AI generation, and that dry:true returns a preview without saving. That is exactly the cost/destruction/preview context an agent needs but cannot infer from structured fields.

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, front-loaded with what the tool does and the destructive replace semantics. Nothing is padding, though the lifecycle sentence could be tightened and the generation-cost note sits mid-block rather than up front.

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?

A destructive, quota-consuming mutation with no output schema and full annotation coverage is well served here: replacement, cost, preview, and cadence are all stated. It does not say what the digest is used for or that get_material reads it back, which is a minor residual gap.

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 100%, and the description largely restates it (8 https pages, 6,000 characters, dry preview). It adds one genuinely new constraint – that the URLs must be the brand's own website – but otherwise adds little beyond the schema, so baseline 3 applies.

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 (builds or rebuilds) and resource (the account's material digest), and enumerates the exact inputs it consumes: up to 8 https pages of the brand's own site, optional notes, and the account's top posts. It is clearly distinguishable from get_material, its read counterpart.

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?

"Applies once per account before the first generation, and again when the website changes" gives a concrete when-to-invoke rule and an implicit when-not. It never names an alternative sibling (e.g. get_material for reads, generate_posts for the downstream step), so the routing is clear but not fully enumerated.

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