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

Annotations only cover readOnly/openWorld; the description adds genuinely non-obvious traits: results come from a residential-proxy scrape of the public site, logged-out visitors see a limited result set, descriptions are truncated at 600 characters, and calls are billed $0.002 USDC via x402 with failed calls free. That billing and data-completeness disclosure is exactly what an agent needs before spending money.

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-loaded with source and purpose, then source/pricing detail; every sentence carries useful information. The long enumeration of return fields is somewhat redundant given an output schema exists, which is the only inefficiency.

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?

Covers source, coverage limits, truncation, cost and billing failure semantics, and even total-count availability – everything needed to call it correctly and interpret the response. An output schema handles the return shape, so nothing material 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%, so the baseline is 3; the description earns an extra point by quantifying the page size ('10 per page, up to page 5'), which lets an agent plan pagination and estimate total retrievable volume alongside the returned 'total count'. The keyword parameter is only illustrated by the schema example, not by the description.

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?

Opens with a specific verb+resource+source: 'Upwork job search: the newest freelance jobs for a keyword.' The Upwork qualifier immediately separates it from the dozens of sibling job-board tools (indeed, dice, wellfound), and the enumerated return fields make the payload shape unambiguous.

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 by the keyword-search framing and the page 1-5 ceiling, but the description never states when to pick this over a sibling board or when not to use it. It also doesn't mention whether results are sorted strictly by recency (relevant vs newest ordering), which an agent choosing between boards would want.

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