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

Discloses useful behavior beyond annotations: the subscription cursor is kept server-side, and ad-hoc mode relies on a since timestamp. However, it does not explain the mark_seen parameter (default true) or how a call affects the stored cursor, which matters given readOnlyHint=false.

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, load-bearing sentences: the first defines the output, the second explains the two calling modes, and the third gives agent-facing consumption guidance. No schema facts are repeated, and the identifying 'since you last looked' concept is front-loaded.

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 12-parameter tool with no output schema, the description covers the dominant usage paths and names core output categories. It still leaves important behavior unexplained, particularly mark_seen/cursor advancement and the filter parameters, and the return shape is only sketched.

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?

With schema description coverage at only 8%, the description adds real meaning for the main mode parameters: subscription_id/subscription_token, postal_code/city/region, radius_miles, and since. It only implies kinds through 'haves and wants' and leaves limit, mark_seen, categories, and keywords without semantic explanation.

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 clear, specific scope: 'What's new near an area since you last looked,' then names the result categories: new haves and wants within the radius, counts, and anonymous accepted-deal counts. This distinguishes it from a generic search or match tool through the recency/cursor framing, even though it does not explicitly name a sibling.

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 explicit guidance on the two calling modes: subscription_id + subscription_token for a server-kept cursor, or postal_code/city/region + radius_miles + since for ad-hoc checks. It also instructs the agent on how to consume results ('Read the results against what your human owns or needs and raise only what applies'), but it does not name alternative tools or state when not to use this one.

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