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

Annotations declare readOnly/openWorld/idempotent=false, but the description adds behavior the annotations cannot: retrieval is live at the moment of asking rather than from a stored copy, results must be attributed with sources and timestamps, and result fields must be quoted verbatim. These are non-obvious output and process expectations that materially change how an agent behaves.

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?

Purpose and freshness are front-loaded, and the operational warnings are grouped at the end. It is a bit long and the caps-emphasized 'QUOTE THEM' sentence restates an already clear point, but each sentence does carry actionable content.

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 an output schema present and 100% schema description coverage, the description only needed to cover freshness semantics, the `near` prerequisite, and output-usage rules — all present. Minor gaps remain around limits/rate behavior and empty-result handling, but nothing an agent needs to call 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%, so the baseline is 3; the description exceeds it by stating a cross-parameter constraint not expressible in the schema (place types require `near`) and by explaining that lat/lng are the right choice when the conversation states the user's location instead of inferring a place name.

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 (look up) and resource (real, current info from open public sources) and enumerates the catalogues covered (jobs, hospitals, banks, schools, etc.), which clearly separates it from siblings like search_marketplace or query_document. The live-read scope (current, not stored copy) further pins down what this tool uniquely is.

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?

Gives concrete operational guidance: place types REQUIRE `near`, use lat/lng instead of guessing 'near me', and do not web-search for a detail already present in results. It stops short of naming a sibling alternative or stating when *not* to use this tool (e.g., versus discover_sources), so it is strong but not exhaustively routing.

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