Journeyed: Los Angeles hotel facts

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

Annotations already cover readOnly, idempotent, non-destructive and closed-world, and the description adds substantial behavior on top: the two return shapes (sourced answer with source URL and checked date vs. direct answer plus top hotels and page URL), the grounding constraint that only published page content is returned, and the exact matched=false fallback. This is exactly the kind of value-beyond-annotations the dimension rewards.

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 routing purpose, then each subsequent sentence carries distinct information: return shapes, grounding rule, failure mode, exclusions. No filler or repetition, and no sentence could be removed without losing a behavior an agent needs.

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 spelled out, and the annotations cover the safety profile; the description nonetheless covers input intent, both success shapes, the failure shape, and hard topic limits. Nothing needed to select or invoke 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 description coverage is 100% with an example, so the baseline is 3. The description still adds meaning by specifying that the question is plain-language and must name either a hotel or a place, and by clarifying which question topics will not match, which shapes what a caller should put in the single parameter.

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 precise verb and resource: routing a plain-language LA hotel question to the published Journeyed page that answers it, and it explicitly distinguishes the two question shapes (named hotel vs. place). It never names or contrasts sibling tools like search_hotels or hotels_near, so an agent must infer the boundary, keeping it short of a 5.

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 clear context for when it applies (plain-language questions answerable from published pages) and explicit exclusions (cannot answer about room prices, availability, or guest reviews), plus the no-match behavior. It stops short of naming an alternative tool for those excluded cases, so the 'when not to use' guidance is only partial.

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 annotations, it discloses the ranking methodology (a published formula), the returned evidence types (points, awards, hotel class, verified facts, distance), and the editorial policy that there are no guest reviews, no prices, and no paid placements. That policy context is not derivable from annotations or 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 core purpose is front-loaded in the first sentence, followed by return shape, ranking policy, and the input constraint. Dense and mostly waste-free, though the quoted-example parentheticals and the 'Best means...' clause add some length.

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 annotations covering safety and an output schema covering response shape, the description still fills the important gaps: ranking basis, evidence provenance, editorial independence, and the at-least-one-input rule. An agent has everything needed 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 coverage is 100%, so the baseline is 3, but the description adds a real constraint the schema does not express: at least one of place or need must be given (the schema lists no required parameters). It also clarifies that limit returns fewer hotels while the full list URL is still provided.

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 ('the published Journeyed best-of list') plus the two input modes (a place or a need across Los Angeles). It is clearly separable from siblings like search_hotels, hotels_near, and get_hotel.

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 tells the agent to supply a place or a need, with at least one required, and points to list_places for discovering covered places. It does not explicitly state when to prefer search_hotels or hotels_near over this tool, so no exclusion guidance is given.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add deeper semantics — and it does: facts carry a source URL and checked date, the Journeyed Score is accompanied by what backs it, and critically the "unknown" list means not-on-record, not that the hotel lacks the amenity. That distinction materially changes how an agent reports 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?

Purpose is front-loaded in the first clause, followed by the fact inventory, the usage rule and the exclusions. The long parenthetical fact list is dense but each item maps to a real query an agent might field; only minor tightening is possible.

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 structure need not be re-explained, and the description instead covers the things structured fields cannot: what domains of fact are in scope, what is deliberately absent, and how to interpret the unknown bucket. Nothing needed to call 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?

With one parameter at 100% schema coverage, the schema already documents accepted forms (current/former name or journeyed.org URL) and gives examples. The description adds no syntax or format detail beyond that, so it sits at the baseline for a fully-documented single parameter.

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?

Names a specific verb+resource — the fact sheet Journeyed holds for one Los Angeles hotel — and enumerates the exact fact categories covered (parking price, fees, pet rules, check-in/out, scores, distances). This is clearly distinguishable from sibling tools like search_hotels, best_hotels and hotels_near, which operate on sets rather than one named hotel.

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 it for any question about a named hotel" gives a clear positive trigger, and "It holds no reviews, room prices or availability" provides negative scope that steers the agent elsewhere. It does not name the specific sibling to use instead (e.g. get_report or search_hotels) for those excluded cases, so it stops just short of full routing guidance.

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, idempotentHint, destructiveHint=false and a closed-world hint, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: what the payload contains (headline numbers with sample sizes, method caveats, page URL, CSV link), which tells the agent this is a read-only aggregate report with provenance. It does not cover pagination or rate limits, keeping it below a 5.

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?

One dense paragraph, but front-loaded with purpose and scope before the inventory of contents, and every clause earns its place (topics, return contents, usage rule, enumeration trick). The topic enumeration is somewhat long but maps to the parameter's allowed values.

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 this tool: an output schema exists and the description still summarises the return shape, annotations carry the safety profile, and the usage rule plus enumeration instruction leave no ambiguity for a single optional-parameter report 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?

There is a single optional parameter and schema coverage is 100%, so the schema already documents 'topic' fully, including the omit-to-list behavior. The description's enumeration of topics largely restates the schema, so baseline 3 is appropriate rather than added value.

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 (a Journeyed data report) with explicit scope: 'Los Angeles area hotels as a whole' and enumerates the concrete subject matter covered. It explicitly distinguishes itself from the one-hotel tools with 'not for one hotel', so an agent can tell it apart from get_hotel without opening either 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?

Gives explicit when-to-use ('market-wide statistics'), when-not ('not for one hotel'), and how to enumerate available reports ('Call it with no topic to list the reports'). The alternative path (get_hotel for a single property) is implied clearly enough that routing is 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 readOnly/idempotent/non-destructive/no-open-world, so the safety profile is covered. The description contributes beyond that: what each result contains (straight-line distance, walking minutes, driving distance, sourced facts with source URL and checked date) and, importantly, the fallback behavior when no page covers the need there — it returns a message listing covered needs.

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 first sentence front-loads purpose and scope, and the later sentences cover return fields and the no-page fallback without fat. The long parenthetical enumeration of needs largely duplicates the schema's need description, which is the one place it 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?

For a read-only lookup with a full output schema, the description covers the remaining gaps: single-need constraint, result contents, and the not-covered fallback. Return-value detail is slightly redundant given the output schema, and the absence of routing versus sibling hotel tools is the only real hole.

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 and the schema already lists the need vocabulary and limit bounds. The description adds the non-obvious semantic that only ONE need may be supplied at a time, and frames limit against the full-list URL, which the schema does not convey.

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 resource and scope: ranked hotels near a named Los Angeles place, optionally filtered by a single need. It is far more specific than a tautology and implies the curated 'journeyed.org page' model that differentiates it from search_hotels/best_hotels, but it never names those siblings, so an agent must infer the boundary itself.

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: have a place, optionally add one need, and use list_places to discover valid place names. There is no explicit when-not guidance and no routing against the sibling hotel tools (search_hotels, best_hotels, get_hotel), which is the main thing an agent needs to choose 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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed (openWorldHint=false) world, so the safety profile is covered. The description adds real behavioral context beyond that: the coverage domain is limited to places that actually have hotel lists, and each entry exposes a page URL plus filterable 'needs' facets. Only the exact response shape is left to the output 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?

Two sentences, front-loaded with the resource scope and the routing guidance. Slightly dense in the first sentence but every clause (coverage, URL, filterable needs, optional kind) carries information an agent needs.

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 format need not be spelled out, and the description still supplies the domain constraint, the discovery intent, and the downstream tools. For a zero-required-parameter lookup tool this is complete enough to call correctly on the first attempt.

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% and the single 'kind' parameter already enumerates the accepted values (airport, venue, convention, attraction, beach, campus, hospital, transit, employer, area). The description only restates that filtering by kind is optional, adding no semantics beyond the schema, 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?

States a specific resource ('landmarks, venues, airports, attractions and neighborhoods Journeyed has hotel lists for') with an explicit geographic scope (Los Angeles area) and what each entry carries. It is clearly distinguishable from siblings like search_hotels and get_hotel, which return hotel data rather than place coverage.

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 two concrete use cases ('check that a place is covered' and 'find the exact name to pass to hotels_near or best_hotels'), naming the alternative tools it feeds into. The optional kind filter is also flagged as optional, so the agent knows the call works with no arguments.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds the meaningful behavioral constraint that matching is name-based only, which explains why keyword-style needs (parking, pets) fail here. Return contents are mentioned but an output schema exists, so that portion adds less.

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?

Four tight sentences, zero filler, with purpose and scope front-loaded before usage and the sibling hand-off. Every sentence carries either a routing rule or a constraint.

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?

Output schema covers return shape and annotations cover the safety profile, so the description only needs to supply scope, routing, and matching semantics — all present. Nothing required to call it 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 all three parameters are already documented with examples and limits. The description restates the query fields and the optional proximity filter but adds no syntax or format detail beyond the schema, so the baseline of 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?

Specific verb (find) plus resource (hotels) plus scope (Los Angeles area) and the matching fields (name, former name, brand, city). It also signals its role relative to get_hotel and hotels_near, so an agent can distinguish it from siblings without opening another 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?

Explicitly states when to use it ('to get the exact hotel before get_hotel', 'to list a brand's hotels near a place') and when not to ('for a need such as parking or pets use hotels_near'). This is a complete routing instruction with a named alternative and the condition that selects it.

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