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

Annotations already cover read-only and open-world, so the description earns credit for adding the 1-credit cost and for disclosing that results include neighbouring locations, not just the queried city. No mention of failure behavior when a place name is ambiguous or unmatched.

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 sentences, front-loaded with the action, then the endpoint contract, then the rationale, then cost. Every sentence carries distinct information with no 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?

With no output schema, the description usefully characterizes the return: location ids plus neighbouring locations. Cost is disclosed. The only real hole is the undocumented cache_max_age parameter, which leaves an agent guessing about a secondary option.

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?

The schema documents 'query' with an example, but 'cache_max_age' is undocumented in both schema and description at only 50% coverage. The description adds no parameter meaning beyond restating 'resolve a place name', so it does not compensate for the gap.

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 ('Find a Marketplace location') and goes further by naming exactly what the call produces ('Marketplace location ids /v1/facebook/marketplace/search accepts'). This makes it unmistakable versus facebook_marketplaceSearch, which consumes those ids rather than producing them.

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?

'Marketplace is city-scoped, so this is how you search a city you are not sitting in' gives a clear situational trigger and points at the consuming sibling. It stops short of an explicit sequencing instruction ('call this first, then pass ids to marketplaceSearch') and lists no exclusion conditions.

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