HotelMonitor hotel prices

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

Goes well past the annotations: it discloses that no verdict is returned when data is insufficient, that prices are tax-inclusive nightly figures for two adults from past scans rather than live quotes, and that the Agoda share is estimated tax. It also explains the page_url and book_url outputs, which is meaningful behavioral context an agent cannot infer from readOnlyHint.

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 core judgment and its trigger come first, followed by data caveats and output notes, so it is well front-loaded. It is somewhat dense across five sentences, but each carries distinct information rather than restating the 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?

For an 8-parameter tool with an output schema, it supplies everything that matters: what the verdict means, when no verdict appears, the provenance and currency basis of prices, and the purpose of the returned links. Nothing an agent needs to call or interpret this 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 75%, and the description adds interpretation the schema lacks: the price is a tax-inclusive nightly figure for two adults, establishing the basis against which the quote is judged. It also explains that book_url has dates filled in, tying checkin/checkout to output. It says nothing about the destination slug format or the 'via' attribution parameter, which the schema covers only partly.

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: judging whether a quoted hotel price is high, low or usual for that hotel in that month, based on HotelMonitor scans. It is clearly distinguishable in substance from find_hotel_deals and get_destination_prices, though those siblings are never named.

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 triggering context ('Use it when someone asks "is this a good price?"'), which is exactly the routing signal an agent needs. It does not say when to prefer find_hotel_deals or get_destination_prices instead, so exclusions are absent.

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 readOnly/idempotent/non-destructive annotations, it discloses the result cap (at most 20), the provenance and staleness of data (past scans, not a live quote), the pricing basis (two adults, tax-inclusive, Agoda share is an estimated tax), and what the returned URLs are for. That is exactly the kind of context annotations cannot carry.

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, front-loaded with what a deal is, then filters, then price caveats and return fields. Dense but nearly every clause earns its place; the Agoda tax-estimate parenthetical is the one detail that could be trimmed.

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?

Complete for a filtered discovery tool: filters, result limit, data freshness, price basis, and guidance on the two returned URLs. With an output schema present, it still usefully explains the semantics of page_url and book_url without over-specifying return structure.

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 description adds real meaning beyond the schema: filters are all optional ('optionally for one destination, check-in month or maximum nightly price'), and prices are tax-inclusive nightly figures for two adults, which gives max_price a unit context the schema only partially supplies (GBP). The 'via' parameter is documented in the schema but not echoed 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 specific verb+resource with scope: 'current hotel deals... hotels priced below their typical level,' capped at 20 results, with optional destination/month/price filters. It implicitly separates itself from the sibling price-lookup tools by stressing these come from past scans and are 'not a live quote,' though it never names check_hotel_price or get_destination_prices directly.

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?

Usage is implied rather than stated: an agent can infer that book_url/page_url are the path to a live price check, and that this tool is for deal discovery rather than a specific quote. There is no explicit 'use this when X, use check_hotel_price when Y' routing or exclusion.

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?

Adds substantial behavior beyond the annotations: data comes from past scans, is tax-inclusive for two adults, includes an Agoda tax estimate, omits months with too few scans, and is not a live quote. It also explains page_url and book_url behavior, which is valuable context for interpreting results.

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 compact for the amount of useful information it conveys, with the primary purpose and use case front-loaded before caveats about data freshness and links. Every sentence adds value.

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 output schema exists, the description is sufficiently complete: it covers data provenance, the distinction from live quotes, omitted months, and what the returned links are for. Combined with the rich read-only annotations, an agent has what it needs to invoke and interpret the tool 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?

The schema already describes both parameters at 100% coverage, including the destination slug format and the optional via attribution. The description does not add further parameter-level meaning, so the baseline 3 is appropriate.

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: typical nightly hotel price by month for a destination over coming months, plus cheapest months. It clearly distinguishes itself from a live quote and from generic hotel search, though it does not name the sibling tools it is not.

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, "when is it cheapest to go to X?", and clarifies that results are historical estimates, not live quotes, with booking URLs for checking current prices. It does not explicitly exclude or compare against check_hotel_price and find_hotel_deals, so it falls short of a 5.

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