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

Annotations only cover safety/read-only semantics; the description adds substantial behavioral context the annotations cannot: source restriction (own website menus only), return payload shape (price, match rationale, unchecked constraints, menu source and date), the no-invention guarantee, live-call metering, and the no-menu-on-file fallback.

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?

Long but front-loaded: purpose and trigger phrases come first, then inputs, then output/behavior guarantees. Slightly dense with overlapping example phrasings, but nearly every clause carries distinct information.

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 15-parameter, open-world, output-schema-bearing tool, the description covers sourcing, guarantees, fallbacks, and sibling routing. Return values need not be re-explained given the output schema, so nothing critical 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 description coverage is only 20%, so the description must compensate, and it does for the core inputs: query, place_id, name, location, max_price, food_status, and include/exclude constraints. It is silent on lat/lng, limit, radius_m, party_size, and kosher_only, leaving part of a 15-parameter surface undocumented.

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?

Specific verb (recommend) plus a precisely scoped resource: individual dishes drawn only from a restaurant's own published menu. It explicitly contrasts itself with verify_kosher and states it never pulls from ordering platforms or review sites, so the agent can distinguish it from every sibling without opening a 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?

States it is the 'first choice' for what-to-eat/order queries, gives concrete trigger phrases ('best tuna dish here', 'dairy options'), explains the two input modes (place vs. location search), and routes the kosher question to verify_kosher. When-to-use, when-not, and the alternative are all explicit.

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