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

Annotations only declare readOnlyHint=true and openWorldHint=false, so the description carries the burden and does add real value: determinism, no LLM, a concrete $0.01 USDC price, and the exact 402 payment-and-retry flow with header names. What it omits is equally behavioral — there is no statement of rate limits, budget bounds/defaults, or failure modes beyond missing payment, and 'POST documents' sits in mild tension with readOnlyHint=true (it is a compute call, not a write, but that is never clarified).

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 short sentences, front-loaded with the operation and return shape before cost and the payment escape hatch. Every sentence earns its place, with no restatement of the tool name or title.

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 paid compute endpoint with no output schema, this covers inputs, output shape, determinism, price, and the exact retry mechanism — enough to call it correctly. It leaves budget semantics (defaults, max, units) and non-payment error behavior unstated.

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 67%, and the description adds meaning the schema does not: budget governs how much output fits, query drives passage ranking, and documents may be chunks with offsets returned. It stops short of giving budget units, defaults, or limits, so the parameter picture is improved but not complete.

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 concrete operation on a concrete resource: submit documents plus a token budget, get back deduplicated, query-ranked, whitespace-compressed context with source offsets and a token estimate. That combination is distinctive enough to separate it from siblings like html_to_rag, url_to_markdown, or document_search without opening any schema.

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?

Usage is implied rather than stated: use it when you need ranked passages compressed into a token budget, and use the payment retry path when the first call returns x402 requirements. There is no explicit when-not guidance and no named alternative among the many retrieval/convert siblings.

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