Map Combiner

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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavioral detail beyond that — short links are expanded (implying outbound fetching), order is preserved, and overlapping endpoint stops are deduplicated. It does not cover failure modes for invalid or unreachable links, 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?

Three short sentences, all load-bearing: purpose and motivation first, then two behavioral guarantees. No filler or restatement of the tool name.

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?

No output schema exists, and the description does at least indicate the result is a single combined link. It stops short of specifying the exact return form (URL string vs. object) or error behavior when a link cannot be expanded, a minor gap for an otherwise simple two-parameter tool.

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%, with both parameters documented including the minItems 2 / maxItems 25 bounds. The description reinforces ordering ("all stops in order") and the overlap rule, but the latter merely restates the mergeOverlap schema text, so it adds little beyond the schema — baseline 3.

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 ("Merge several Google Maps directions links into one link") plus the motivating constraint (10-stop limit per route). It is clearly distinguishable from the sibling list_link_stops, and the output shape (one combined link) is stated up front.

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 an explicit trigger condition: use this to get past the 10-stop limit per route. It also notes that short links are accepted/expanded, which prevents an agent from pre-resolving them. No explicit when-not or named alternative, so not a 5.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety and network profile is covered. The description adds one genuinely useful behavior note — results reflect MapCombiner's own interpretation rather than ground truth — but says nothing about short-link resolution, fetch failures, or what a stop record contains.

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 sentences, no waste. What the tool returns is front-loaded, with the usage guidance and alternative following.

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 one parameter, no output schema, and annotations carrying the safety profile, the description covers the essentials and even characterizes the return as ordered stops. It stops short of describing the fields per stop or behavior on unresolvable short links.

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% and the single url parameter is fully documented there, including both full and short link forms. The description adds no semantics beyond the schema, so the baseline 3 applies.

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 resource and scope: the ordered stops of a single Google Maps directions link, qualified as 'as MapCombiner reads them.' That qualifier distinguishes it from a raw URL parser, but it never mentions the sibling combine_map_links, so the boundary with the actual sibling is only implied.

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 an explicit use case ('check links before combining') and an explicit alternative with the condition that selects it ('For coordinates, distances or CSV/KML export, use MapParser (parseUrl)'). An agent can route correctly without inference.

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