search_deals

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

No annotations exist, so the description carries the full burden and does so well: loose token-based matching, the `relevance` block, that `drop_irrelevant` relocates weak matches to `related` rather than deleting them, and the critical server-side (`include_expired`, `sort`) versus locally-applied filter split. These are exactly the non-obvious behaviors an agent needs.

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 paragraphs, front-loaded with the highest-value caveat (no catalogue behind it), then matching behavior, then the server/local filter trap. Every sentence carries information an agent would otherwise get wrong; nothing is filler.

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 11-param, no-annotation, no-output-schema tool, the description covers the essentials — result character, empty-result legitimacy, `relevance`/`related` shape, and filter execution. It stops short of explaining pagination interplay and what `temperature` means, which leaves minor gaps.

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 0% across 11 params, so the description must compensate; it adds real meaning for the non-obvious ones (`drop_irrelevant`, `include_expired`, `sort`, `size`) and the server-vs-local execution model. It leaves `kind`, `store`, `max_price`, `min_temperature`, and `free_shipping_only` to inference from their names, so compensation is partial but substantive.

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 ('Search deals that Pelando users have posted') and immediately characterizes the corpus ('community postings, NOT a catalogue'), which is the decisive fact distinguishing it from get_deal or browse_feed. An agent can tell what it retrieves without opening the 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?

It gives strong usage-shaping context — that mainstream terms can legitimately return nothing, and that most filters run locally so a narrow filter plus small `size` may under-return — but it never explicitly names alternatives (get_deal, browse_feed, assess_deal_quality) or states when-not-to-use it. Clear context, no explicit routing.

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