HotelRefund Price Tracker

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

With readOnlyHint=true already provided, the description adds substantial behavioral detail: it enumerates the computed fields and discloses the transient awaiting_first_price state for newly created trackings. This goes beyond the annotation and gives the agent accurate expectations.

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 focused sentences: the first front-loads the action and result fields, the second covers an important edge case. No filler or redundancy.

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-required-parameter, read-only tool with no output schema, the description covers what the agent needs: what is returned, the scope of the time series, and the early-life behavior. It is sufficiently complete.

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% because the parameter already documents that tracking_id comes from track_hotel_price or list_tracked_hotels. The tool description adds general context but no additional parameter format, constraints, or examples beyond what the schema provides.

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 opens with a specific verb and resource: 'Return the recorded prices for one tracking', and enumerates the exact result contents (current, first, lowest, highest, percentage change, trend, time series). This clearly distinguishes it from siblings that search, list, or create trackings.

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 establishes clear context: it operates on one existing tracking identified by tracking_id, and even notes the post-creation edge case. It does not explicitly name alternatives or say when not to use it, but the context is sufficient among the sibling tools.

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?

With readOnlyHint and openWorldHint already set, the description goes further: only discounts >=5% are kept, uncached cities are fetched live at most once per 6 hours, no-arg calls return one best per city, and a city call caps at 6 results. 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?

Three sentences pack the core purpose, filtering rule, argument-dependent behavior, caching, and a return-field note. It is dense but front-loaded with the most important verb+resource, and no sentence is 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?

Given the three optional params, the schema descriptions, and the safety annotations, the description covers input modes, defaults and limiting, caching, and at least the key return field (booking_url). With no output schema, a fuller field-by-field return list would be nice, but nothing needed to invoke the tool correctly is 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?

Schema coverage is 100%, so the baseline is 3; the description adds value by specifying the no-argument world list behavior, the up-to-6 cap for city calls, the live-fetch/caching rule, and booking_url in results. It doesn't need to restate the 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 opens with a specific verb and resource ('List today's biggest observed hotel discounts') and immediately fixes the comparison method (Agoda live rate vs Agoda's own listed rate, 5% threshold). This is enough to distinguish it from siblings like search_hotels or list_tracked_hotels, even without naming 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?

It gives clear invocation context: omit arguments for the worldwide one-best-per-city list, pass city or city_id for up to 6 current deals, and city_id overrides city. It doesn't explicitly name sibling alternatives or state when not to use the tool, so it isn't a perfect 5, but the conditions are unambiguous.

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; the description adds useful behavioral context: all trackings are public, results are sorted by biggest price drops first, and each item includes price, change, stay dates, and URLs. This goes beyond the schema and annotations without contradicting them.

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, information-dense sentence that front-loads the main action and scope, then efficiently lists the returned fields and sorting behavior. No filler or redundancy.

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 is simple with one optional parameter and a clear read-only operation. The description covers what is returned, the sorting rule, and the public nature of the data, which is sufficient given the absence of an output schema.

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?

There is only one optional parameter, limit, and the schema already documents it with a default and valid range. The description adds no new meaning to the parameter, 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?

The description states a specific verb ('List') and a clear resource ('hotels currently being tracked'), plus the exact fields returned and the sort order. It is easy to distinguish from siblings like search_hotels or list_hotel_deals because it is specifically about tracked hotels.

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 clearly implies the use case: retrieving currently tracked hotels rather than searching all hotels or listing deals. It does not explicitly name alternatives or exclusion conditions, but the scope is unambiguous enough for an agent to select it correctly.

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?

Beyond the readOnlyHint annotation, the description discloses non-obvious behavior: it resolves to the 'best-matching' catalog city, returns other_city_matches on ambiguity, and requires passing city_id to switch searches. It also explains the output's key linkage to track_hotel_price. This gives the agent accurate expectations beyond the schema.

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 two sentences with no filler. It front-loads the primary purpose, then packs the disambiguation rule and downstream integration into a single dense but readable second sentence.

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 read-only search tool with 100% schema coverage and no output schema, the description covers the essential operational details: input forms, language support, matching behavior, ambiguity resolution, and the significance of the returned agoda_hotel_id. Nothing critical is missing for an agent to call 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 coverage is 100%, so the baseline is 3, but the description adds cross-parameter meaning: city_id comes from a previous other_city_matches result and overrides city, and the hotel id returned is what track_hotel_price requires. This relationship guidance is not fully evident from the parameter descriptions alone.

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 specific action ('Search HotelRefund's hotel catalog'), a clear resource, and the result behavior: resolving a city/region/airport name into a catalog city and listing hotels. It also differentiates itself from siblings by naming the agoda_hotel_id that track_hotel_price requires, making its role in the workflow unmistakable.

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 gives concrete guidance on the disambiguation flow: when several cities match, use one of their city_id values instead of city. It also implies this tool is the prerequisite lookup before track_hotel_price. It does not explicitly enumerate when to prefer list_hotel_deals or get_price_history, but the resource and workflow relationship are clear enough.

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 goes well beyond the annotations by explaining what happens after invocation: the price is checked several times per day, every observed price is recorded, duplicates return the existing tracking, and the response contains specific URLs. The idempotentHint is explicitly supported by the deduplication language, and no contradiction exists with readOnlyHint=false or destructiveHint=false.

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 dense sentences carry all essential information with no filler. The action, constraints, behavioral consequences, idempotency, and key response fields are all covered economically and in a logical order.

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?

Given that there is no output schema, the description rightly names the two most important response fields, booking_url and track_page_url. It also covers the core lifecycle behavior (automatic checks and deduplication). It leaves out minor details such as how to later reference the created tracking, but nothing essential to invoking the tool correctly is 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?

Schema description coverage is 100%, so the formal parameters are already fully documented. The description adds context about 'one stay' and the YYYY-MM-DD format, but it does not materially deepen the meaning of currency, language, or the hotel id beyond what the schema already states.

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-resource pair ('Start ... price tracking of one hotel') and clearly states the scope: one agoda_hotel_id, one stay, and automatic price checks. It inherently distinguishes this tool from siblings like list_tracked_hotels or get_price_history by framing this as the action that initiates tracking rather than reading or listing it.

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 gives clear context for when to use the tool: after obtaining agoda_hotel_id from search_hotels, for a specific date range. The duplicate-return behavior also implies a sensible 'use it even if already tracked' guideline, but it does not explicitly name alternatives or state when another sibling should be used instead.

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