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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds genuinely new behavior: null for unstated fields rather than invented values, and a per-call cost of 0.025 USDC across five chains. This is exactly the extra context annotations cannot carry.

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 tight sentences: use condition, output contract, cost. Every sentence carries distinct information and the when-to-use clause is front-loaded ahead of the mechanics.

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?

Output schema exists so return shape needn't be repeated, yet the description still clarifies the null semantics that govern the schema's values. With only two fully documented params and a clear cost/authorization note, nothing needed to invoke it correctly is missing.

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 both params are documented in-schema, including the 20-field/2 KB constraint. The description restates the field count and type palette rather than adding syntax or format meaning beyond what the schema already supplies, so the 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+resource: extracting named fields from a page or PDF into JSON. Clear enough to distinguish from raw-text siblings like get_ocr/get_pdf_markdown, but it never names those alternatives, so the agent must infer the distinction.

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?

"Use when an agent needs named fields from a page or PDF" gives a clear triggering condition. It stops short of stating when NOT to use it or pointing to the sibling extraction tools, so the routing guidance is contextual rather than explicit.

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