Fleet Route Optimizer

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely non-redundant behavior: the returned payload is exactly the shape optimize_routes accepts, which tells the agent the output is directly reusable.

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 with the output contract front-loaded and the usage instruction second. Nothing is padded or redundant.

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, but the description characterizes the return value well enough for downstream use. The remaining gap is that it never tells the agent where valid 'name' values come from, even though list_route_examples is a sibling.

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 50%: lang is documented in the schema, but 'name' carries no description anywhere. The parenthetical (depot, stops, vehicles, windows) describes fields of the returned example, not the input parameters, so it doesn't close the gap on what 'name' accepts or where valid values come from.

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 ('return the full input of one example') and pins the output contract to the sibling optimize_routes. This cleanly distinguishes it from get_route_result (results, not inputs) and list_route_examples (many, not one).

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 workflow: fetch the example, then edit depot/stops/vehicles/windows for the user's situation, implying the example feeds optimize_routes. It stops short of explicit when-not-to-use guidance or a pointer to list_route_examples for discovering valid names.

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 cover the safety profile (readOnly, non-destructive), so the description's added value is the polling semantics and the 15-minute post-completion expiry — genuinely useful operational context the agent cannot infer from annotations. It stops short of disclosing error/intermediate states or what a completed result 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?

Three short sentences, front-loaded with the resource and follow-up with the polling and expiry rules; no filler. The opening phrasing ('a job that returned status running') is slightly awkward but does not waste words.

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 never says what the fetched result contains (route geometry, legs, status field), which an agent needs to use the return value. Polling and expiry are covered, but the return payload is a real gap for a 2-parameter async-result 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 0%, so the description must carry parameter meaning. It explains that wait_seconds bounds the wait ('Waits up to wait_seconds') but omits the 0–45 constraint, and job_id is only implied by the phrase 'an optimize_routes job'. Partial compensation for a zero-coverage schema.

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?

The description names a specific verb ('Fetch') and resource ('the result of an optimize_routes job') and ties the tool to its sibling optimize_routes, making the async-job relationship explicit. An agent can distinguish this from get_route_example/list_route_examples without opening any 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?

It gives a clear usage pattern: call while status is 'running', wait up to wait_seconds, then call again. It does not, however, state when to prefer this over the sibling example tools or what to do once the job finishes, so an explicit exclusion is missing.

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, destructiveHint=false, and openWorldHint=false, so the agent knows it is a safe, closed-world read. The description adds that the problems are 'built-in' (not user-created), which is modestly useful, but there is no disclosure of return shape or count.

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 filler, and the core action ('list the built-in example routing problems') is front-loaded before the usage hint. Every sentence earns its place.

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 zero-parameter, zero-dependency listing tool with annotations covering the safety profile and no output schema to explain, this is nearly complete. The only minor gap is that an agent does not know what fields each listed example carries.

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 tool takes no parameters, so per the rubric the baseline is 4. There are no argument names or formats an agent could misinterpret.

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: 'List the built-in example routing problems.' This is clearly distinguishable from the singular get_route_example sibling, though the distinction is left implicit rather than stated.

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?

The second sentence gives an implied workflow ('use one to see a realistic input, or solve it as-is'), which hints at how it pairs with the solve/get tools. However, it never names get_route_example as the alternative or states when this list is preferable to just fetching a known example.

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 mark this readOnly/non-destructive/openWorld, and the description adds substantial context beyond that: solves take 10-60s and longer with many geocodes, real road driving times are used, and the defaults for omitted fields (unlimited capacity, no time windows, 1 vehicle, drop-only-when-unservable) are spelled out. The async 'running' status contract is disclosed, which annotations cannot 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?

Front-loaded with the output contract and solve-time expectations, then defaults, then the async fallback. The embedded JSON example is dense but earns its place by demonstrating the required nesting; the sentence count is proportionate to an 8-parameter nested schema.

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?

There is no output schema, so the description carries the return-value burden and does so fully: stop order, arrival times, load so far, unserved stops, totals, Maps links, warnings. Combined with solve-time and async guidance, an agent has everything needed to call and interpret this 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%, so the baseline is 3; the description goes further by summarizing the defaults applied when fields are omitted and by supplying a minimal worked example that shows the nesting of depot/stops/vehicles. It does not explain the more advanced knobs (capacity2/3, previous_routes, parameters), so it stops short of 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?

The description states a concrete verb and resource ('Plan routes for one or more vehicles from one depot') and specifies the output shape per vehicle, so the agent knows exactly what the tool produces. It is clearly distinguishable from the sibling helpers get_route_example and get_route_result.

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?

Explicit routing logic is given: pass either `example` or the fields below, call get_route_example for complete realistic inputs, and if the result has status 'running' call get_route_result with its job_id. The async handoff and the alternative-sourcing paths are both named, leaving nothing to inference.

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