Place Search

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

Annotations already cover the read-only/open-world/non-destructive profile, and the description adds genuine context on top: review text and web pages are off by default because they cost context, `distance` only appears when coordinates are supplied, and each card carries status/rating/review_count regardless of options. This is behavior the annotations could not convey.

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?

Well front-loaded: purpose and return shape first, then usage, then the opt-in flags in descending importance. It is long, and the "near me"/area-naming rule is stated twice (coordinates paragraph and user_location paragraph), which costs a little density.

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 an 8-parameter tool with nested `places`/`web_search`/`user_location` objects and no output schema, the description supplies everything needed: the card shape substitutes for a missing output schema, and the defaults/opt-in costs for the heavy flags are spelled out. Nothing an agent needs to call it correctly is absent.

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 earns above that by explaining the interplay that the schema lists but does not motivate — `radius` requires coordinates, `user_location` is the fallback when coordinates are unknown and yields no `distance`, and `max_reviews` is only worth setting when review text itself is the question. Minor parameters (`timeout`, `places.count`, web_search sub-options like `time_range`/`include_domains`) get no narrative treatment, so not a 5.

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 specific verb+resource ("Find real-world places") and immediately enumerates the card fields returned (name, category, address, coordinates, phone, hours, status, rating, review count). It also explicitly distinguishes itself from the sibling `search`, which "would return pages *about* places that then have to be read" — an agent can route between them without opening either 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?

Gives explicit when-to-use with sample phrasings ("coffee shops near me", "is this place open on Sunday"), when-to-use alternatives (use `search` for pages about places), and granular routing rules: coordinates vs `user_location` vs neither, when to raise `max_reviews`, when to flip `web_search.enable`. It even states the anti-pattern — sending coordinates to a query that names its own area is unused data.

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