pick_points

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

With no annotations, the description carries the burden and does disclose key traits: the tool is interactive and blocking (it opens a browser and waits for the user), and it depends on an external server being up. It omits what happens when the user never clicks (timeout behavior, failure mode), which matters for a blocking call.

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?

A single tight sentence front-loads the action and follows with the prerequisite and return contract. No filler, though the parenthetical could be structured more crisply.

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?

Output schema exists, so the description need not explain the return shape, though it helpfully notes 'lat,lon' strings and their use in plan_route. The remaining gap is timeout/failure behavior for a tool that blocks on human input.

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 0%, so the description must document both parameters. 'Click 1 or 2 points' loosely hints at `n` but never names it or its bounds, and `timeout_s` is not mentioned at all despite governing how long an agent will block.

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: asks the user to click 1 or 2 points on the planner map and waits for the result. It also names the downstream consumer (plan_route) and the return format, so an agent can distinguish this interactive picker from geocode or route_details 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?

Implies usage clearly: call this before plan_route to obtain 'lat,lon' start/end strings, and it requires `make planner` running. It gives a prerequisite and a purpose in the workflow, but offers no explicit exclusions or alternatives (e.g., when to use geocode instead).

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