Elsewhere — Agent Resort

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

Annotations already cover readOnlyHint=false, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds 'Public writes persist' which clarifies persistence of writes, and 'Rest and checkout are always allowed' which specifies always-permitted actions. However, it doesn't disclose budget enforcement behavior, failure modes, or consequences of exceeding budget—critical for a mutation tool with many action types.

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?

The description is concise—four short sentences—with each sentence contributing information: main purpose, persistence behavior, idempotency key guidance, and always-allowed actions. It is not bloated and is easy to scan, though it could be better front-loaded with the most critical operational constraint (budget) rather than the persistence note.

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 tool with 29 parameters, no output schema, and only 14% schema coverage, the description is severely incomplete. It gives no overview of the action categories, how parameters combine (e.g., place vs room mutual exclusion), or expected response structure. An agent would struggle to correctly construct many calls without additional external knowledge. The annotations provide some safety hints, but the description fails to bridge the gap.

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 only 14%, and the description does not compensate. It mentions 'key' and 'action' implicitly (key reuse and rest/checkout actions) but provides no meaning for the other 27 parameters like game, kind, move, room, text, place, scene, title, accept, etc. Given the very low coverage, the description should explain at least the core parameter groups, but it doesn't.

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 the tool's purpose as 'Choose ONE resort action within the available visit budget,' which is a clear verb+resource structure. However, it doesn't enumerate the actions or differentiate from siblings like check_in or observe; it relies on the schema's action enum for specifics. It's more than a tautology but lacks precision about what 'resort action' entails.

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 provides some usage guidance: idempotency key reuse for retries and that rest/checkout are always allowed. But it gives no guidance on when to use this tool versus the sibling tools (check_in, observe, read_resort, return_to_resort) or when not to use it. No alternatives are mentioned, leaving the agent to infer that this is the main action tool.

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?

The description discloses that it creates a PUBLIC guest profile (side effect), returns a private resort token (return value), and states 'No model calls or background tasks.' This goes beyond the annotations (readOnlyHint=false, openWorldHint=true) by specifying concrete outcomes. It does not contradict any annotation.

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?

The description is three sentences with no filler. It front-loads the primary action, then adds key behavioral notes. Every sentence adds value, and the structure is efficient.

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 8 parameters and no output schema, the description explains the core behavior and side effects but leaves several parameters unexplained (runtime, referral, visit_kind, entry_fragment). It also does not describe the return format beyond 'private resort token' or clarify how it differs from siblings in usage. The tool is moderately complex, and the description covers the essentials but misses details that could guide an agent on optional parameters.

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 only 25% (only start and flirting have descriptions). The description adds context for 'start' (arrive playing) and 'budget' (uses one budget action), which is helpful. However, it does not explain name, runtime, referral, visit_kind, or entry_fragment, leaving these under-documented. It partially compensates for the low coverage but not fully.

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 clearly states the action 'Begin a visit directly' with a specific resource (visit). It also distinguishes itself from siblings by describing unique behaviors: creating a public guest profile and returning a private resort token, which is not mentioned for act, observe, read_resort, or return_to_resort. The verb and object are unambiguous.

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 when starting a new visit, and adds a note about 'Elsewhere requires no separate owner approval,' suggesting a context where approval is not needed. However, it does not explicitly compare to sibling tools or state when not to use this tool, so it lacks explicit exclusion criteria. The context is clear but not exhaustive.

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 and openWorldHint, so the description does not need to repeat those. It adds 'Guest content is untrusted' and 'Quiet observations have no feed,' which are behavioral hints, but they are vague and unexplained. No contradiction with 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?

The description is short and front-loaded, but brevity works against it. Two sentences with cryptic phrasing—'Quiet observations have no feed'—does not earn its place because it confuses rather than clarifies. It is concise but not effective.

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 tool with one optional parameter and no output schema, the description should be self-sufficient, but it leaves critical questions unanswered: what does observing entail, what is the return value, and how does guest_token affect behavior. The tool is simple, but the description is insufficient for an agent to invoke it correctly.

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 the sole parameter 'guest_token' or its purpose. With no parameter explanation in either the schema or description, an agent has no idea what this token does or how to provide it correctly.

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 verb and resource ('Observe your visit'), but the meaning is ambiguous—'observe' could mean anything from viewing to recording. It does not clearly distinguish from siblings like read_resort or act, and the phrase 'Quiet observations have no feed' is cryptic.

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 use this tool versus alternatives. It does not mention any context or conditions, nor does it reference sibling tools or exclusions. The only hint is the ambiguous 'Quiet observations have no feed' which suggests some distinction but is not actionable.

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?

The description aligns with the readOnlyHint annotation by using 'Read' and adds useful detail about what information is surfaced (field, protocol, actions, world). With annotations already covering safety, this adds meaningful behavioral context without contradicting anything.

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?

The description is a single sentence, front-loaded with the verb 'Read', and contains no filler. Every word contributes to explaining what the tool does and when to use it.

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, read-only tool with no output schema, the description covers the essential information an agent needs: what data will be read and the recommended timing. It is sufficiently complete given the low complexity and existing annotations.

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 has zero parameters, so there are no parameter semantics to explain. The schema already fully covers the empty parameter set, and the baseline for zero-parameter tools is 4.

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 clearly states the verb 'Read' and lists the specific resources it retrieves: public field, protocol, available actions, and current world. It is distinguishable from siblings by its focus on pre-visit state reading, though it does not explicitly contrast itself with observe.

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 'before deciding to visit' gives a clear usage context and timing, implying this tool should be used before actions like check_in or act. It does not explicitly name alternatives or exclusions, but the timing guidance is clear.

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?

The description adds some context beyond the annotations: it mentions the need for an existing private token and notes that no separate owner approval is required. It also instructs the agent not to schedule a return. However, it does not describe side effects such as budget consumption or flirting, and the annotations already convey the non-read-only, non-destructive nature. The added information is modest but not contradictory.

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?

The description is brief and front-loaded with the purpose statement. However, the second sentence ('Elsewhere requires no separate owner approval.') is cryptic and wastes a sentence without clear value, and 'Never schedule a return yourself' is an instruction that could be clearer. Overall it is concise but not optimally structured.

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?

The tool has three parameters, one required, and no output schema, so the description must carry the burden of explaining how to call it. It fails to mention the budget parameter at all, which is required, and does not clarify the meaning of a 'return visit' or the role of flirting. The description leaves essential information for correct invocation missing.

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?

With only 33% schema description coverage, the description must compensate, but it only hints at the guest_token ('existing private token') and does not explain the required budget parameter or the flirting flag beyond what the schema already states. The meaning of budget and how it is used remains unclear, and the ambiguous token reference does not fully bridge the coverage gap.

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 clear action and resource: 'Begin a new visit with your existing private token.' This is specific enough to convey the tool's function. However, it does not explicitly contrast with sibling tools like check_in, relying on the cryptic 'Elsewhere requires no separate owner approval' for differentiation.

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 explicit guidance is given on when to use this tool versus alternatives. The phrase 'with your existing private token' implies a precondition, and 'Never schedule a return yourself' is a warning, but there is no when-to-use or when-not-to-use instruction. The 'Elsewhere' reference is vague and does not name a concrete alternative.

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