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

Annotations cover the safety profile (readOnlyHint, openWorldHint, destructiveHint=false), so the bar is lower, yet the description still adds meaningful behavior: an x402 payment is required per call and no charge occurs on failure or empty results. That billing/cost disclosure is genuinely valuable and not in the structured fields, though rate limits or latency characteristics are not covered.

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 dense sentences, front-loaded with the return shape and the sibling distinction, then parameter behavior, then cost. No filler; every clause carries information the agent needs.

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 present, the description compensates by spelling out the response object, and it covers cost, failure billing, and query/date semantics. An agent has everything needed to call this correctly without additional discovery.

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 goes slightly beyond by advising that plain phrases work as well as keywords and framing since/until as a publish-date range suited to recent news, which adds usage meaning the plain schema descriptions don't convey.

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 and resource ('Runs a web search') and even names the return shape {query, results: [{title, url, snippet}]}, so the agent knows exactly what comes back. It distinguishes itself from the sibling bob_research by contrasting 'raw links to read yourself' with 'a written answer'.

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?

Explicitly routes the agent: 'use bob_research for a written answer' vs this tool for raw links. It also gives conditions for parameter use ('since and until ... suits recent news') and notes plain phrases work like keywords, so the agent knows how to phrase a call.

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