nearby_food

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

With no annotations, the description carries the full burden and does meaningful work: it discloses the cross-source nature, the defaults used when no params are supplied (1500m, batch 1), the pagination protocol via page, and the presence of a 'next' suggestion field in the response. Gaps remain: it never explains how latitude/longitude are obtained (the tool cannot locate the user without them) and says nothing about latency, rate limits, or permissions.

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?

Front-loaded with purpose then trigger conditions, and each bullet maps a distinct user utterance to a distinct parameter, so the length is mostly earned. The '★' mapping block duplicates the per-parameter descriptions in the schema, which is mild redundancy but not padding.

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 6-param, zero-annotation, no-output-schema tool, this covers defaults, pagination, and the source mix well enough to invoke correctly without authoring params. It is incomplete on two counts that matter for a location tool: how coordinates are sourced, and how to choose between this and 'what_can_i_eat'.

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 100%, so the parameter-level mapping guidance in the description (industry, radius_m=500, page+1) largely restates what the schema already documents per field. It adds one non-schema rule ('fill the param instead of filtering results yourself'), but that belongs more to usage than to parameter semantics, so this sits at the baseline for fully-documented schemas.

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?

The description states a specific verb+resource: it returns nearby stores plus per-dish affordability, and explicitly notes it spans two data sources (McDonald's MCP + local restaurants). That is far more specific than the name alone. However, it never distinguishes itself from the sibling 'what_can_i_eat', which by name sounds like a competing answer to the same user intent, so the agent gets no disambiguation.

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?

Strong trigger coverage: it names concrete user phrasings ('附近有什么能吃的', '现在吃什么', '有什么推荐的') and maps constrained phrasings to specific parameters, plus a 'don't pre-filter results yourself' rule and the no-argument fallback behavior. It stops short of the top mark because it never states when NOT to use it or names an alternative sibling for the overlapping case.

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