A2APark

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, covering safety. The description adds real behavioral value beyond that: structural errors do not enter the ride or consume a step, while semantically poor but valid payloads do, and it notes the return contents. These are meaningful mechanics not derivable from annotations.

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 tight sentences, front-loaded with the core action then the validation/step rule then the return shape. No filler, and each sentence carries distinct information.

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 complex multi-variant action tool with an output schema, the description covers the essentials: validation strictness, step consumption, and the fact that a next observation is returned. It slightly overlaps the output schema by restating returns, but is complete enough for correct invocation.

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%; the action parameter is richly documented via nested variant descriptions, while runId has no description anywhere. The description clarifies that action variants are constrained by the latest observation and that validation is strict, adding meaning over the raw schema, but leaves runId semantics implicit. Baseline 3 fits.

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 ("Submit one strictly validated action") and resource ("for the ride identified by runId"), which is unambiguous about what the tool does. It does not explicitly contrast itself with siblings like start_ride or list_rides, but the purpose is clear enough to distinguish operationally.

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?

"Use a payload variant allowed by the latest observation" gives procedural guidance on how to select an action, but offers no when-to-use framing relative to siblings (e.g., after start_ride, before get_scorecard). Usage is implied rather than stated, so a 3 is appropriate.

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 safety profile is covered. The description adds genuine context beyond that: the artifact is 'signed,' it reflects exactly one simulated run, and it explicitly is not a safety certification — meaningful framing that shapes how the agent interprets the result.

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 short sentences, front-loaded with the verb+resource and key, followed immediately by the scope caveat. No filler, no restatement of the title.

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 single-parameter read tool with an output schema, the description does not need to explain return values, and annotations already carry the safety profile. What remains missing is error/precondition behavior (e.g., what happens if the run is not completed) and where a runId comes from — small but real gaps.

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 description coverage is 0%, so the single runId parameter is undocumented in structured data. The description identifies runId as the lookup key for a completed ride's run, which is more than the schema offers, but it gives no format, length, or sourcing guidance (e.g., where runId comes from), so the gap is only partially closed.

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 and resource ('Retrieve the signed scorecard') plus the lookup key ('by runId'), and adds a scope disclaimer ('reports this one simulated run and is not a safety certification') that no sibling tool covers. 'Scorecard' is a unique resource among act_in_ride/list_rides/start_ride, so an agent can distinguish it 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?

The phrase 'for a completed MCP ride' implies the precondition (a run that has finished) and the certification disclaimer implies when not to rely on the result. However, it never names an alternative tool or states explicitly when to call this versus inspecting a ride some other way; the guidance is implied rather than stated.

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, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds the useful constraint that only 'public' rides are returned, but says nothing about ordering, volume, or pagination.

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 short sentence, front-loaded with the verb and resource, with zero 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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. The description is nearly sufficient for a zero-param read tool, with only the 'missions' concept left slightly opaque.

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 zero parameters, so per the baseline there is no parameter semantics burden on the description. Nothing is missing or misleading here.

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 clear verb ('Discover') and resource ('rides') and adds the scope qualifier 'public'. It differentiates implicitly from mutating siblings (start_ride, act_in_ride) by being a discovery operation, though it never names 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?

No guidance on when to call this versus get_scorecard or start_ride, and no prerequisites stated. Usage is only inferable from the read-only 'discover' framing.

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=false, openWorldHint=false, and destructiveHint=false. The description adds useful context that the ride is public/simulated, that no real-world system is tested, and that the response includes the first observation and allowed actions. It does not cover auth or rate limits, but the annotation coverage lowers that burden.

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 action and scope, followed by return content and a safety clarification. Each sentence adds distinct value without 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?

For a one-parameter start tool with output schema and annotations, the description covers purpose, simulation scope, and return shape. However, it omits what rideId is and where it comes from, so an agent still lacks guidance on the only required 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 description coverage is 0%, and the description never mentions rideId or explains what it identifies or where to obtain it. The single required parameter therefore lacks both schema-level and description-level meaning, leaving a significant gap for an agent trying to invoke the tool.

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 uses a specific verb (Start) and resource (ride), scopes it to one public simulated ride for this agent, and describes the immediate return value. This clearly distinguishes it from siblings like act_in_ride and list_rides.

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 description implies usage by saying the ride is for this agent to take, but it does not state when to choose this over act_in_ride or list_rides, nor does it give prerequisites or exclusions. Guidance is present only by implication.

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