suggest_placesIdentifies the addresses you ride to and from most often from recent rides so they can be saved as home or work, confirming with you which is which before saving.
Finds the addresses the user rides to and from most often (from their recent rides), so they can be saved with save_place (e.g. as home or work). Ask the user which is which before saving.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=true is consistent with a read-only 'finds' operation, and the description adds value beyond the annotation by disclosing the data source (recent ride history) and the required post-call behavior (confirm with the user before saving). It does not say how many results come back or what an empty result means, which is the remaining gap.
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?
Two tight sentences: the first defines the result and its source, the second defines the required follow-up action. Front-loaded with the outcome, zero filler, nothing redundant with structured fields.
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 parameterless-required, read-only lookup with no output schema, the description conveys enough: what is returned conceptually (frequent to/from addresses from recent rides) and what to do next. The only omission is the meaning and expected range of the limit parameter.
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 single parameter 'limit' has 0% schema description coverage (only type/default/min/max are present) and is never mentioned in the description, so an agent gets no explanation of what it controls beyond the constraints. The description should say it caps the number of suggested addresses returned.
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: 'finds the addresses the user rides to and from most often (from their recent rides)'. This distinguishes it in substance from list_places and search_address by making clear it derives unsaved frequent addresses from ride history rather than reading stored places or searching an address book, though the contrast with those siblings is implied rather than named.
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 a clear usage context ('so they can be saved with save_place, e.g. as home or work') and even prescribes the workflow step of asking the user which address is home vs work before saving. It does not state when NOT to use it or name a competing sibling, so it stops short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.