Hotel Fact Graph

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

With no annotations, the description carries the full behavioral burden. It usefully discloses a key trait: results are observational deltas, not confirmed policy changes, which prevents misuse. However, it says nothing about permissions, capture windows, result completeness, or ordering.

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 terse sentences, front-loaded with the core purpose and immediately followed by the most important caveat. No filler, though the fragments are slightly telegraphic.

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 critical framing (observed vs. confirmed changes) is present, which is the most valuable thing an agent needs. But with no output schema and zero parameter documentation, the definition leaves gaps about return contents and parameter semantics.

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% for both parameters, so the description must compensate. It only notes that the identifiers match get_hotel_facts and that the scope is 'one hotel,' leaving 'domain' entirely unexplained and giving no format or value guidance for 'property_id.'

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 concrete resource ('observed value differences across captures for one hotel') and scopes it to a single hotel, which distinguishes it from the sibling get_fact_changes/get_hotel_facts pair by framing this as a diff view. It does not use a strong action verb, but the resource and scope 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 the use case (seeing what changed over time) and warns that the deltas are not confirmed policy changes, but it never states explicitly when to call this instead of get_hotel_facts or search_hotels. Sibling routing is only hinted at via 'Same identifiers as get_hotel_facts.'

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 no annotations, the description carries the full burden. It discloses the key behavioral quirk that a chain domain returns a property list instead of facts, plus the fact structure (as_of, source_url, evidence), but says nothing about permissions, rate limits, or recency/pagination behavior.

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?

Compact and front-loaded: purpose first, then the parameter preference, then the edge case, then the return shape. Every fragment carries information; only the terse phrasing keeps it from a 5.

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 2-param, no-output-schema, no-annotation tool, the description covers purpose, parameter preference, an important edge case, and the returned fact fields. It is largely sufficient, with the main gap being parameter format expectations.

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 description must compensate. It adds real meaning by preferring property_id and explaining that a chain domain returns a property list, but it never defines the format or expected values of either 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 specific verb+resource ('Latest cited facts for one hotel') and scopes the sources (own website or official register). It is clearly distinct from search_hotels, though it does not explicitly contrast with get_fact_changes.

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 one useful routing hint ('Prefer property_id') and explains the chain-domain edge case, but offers no explicit when-to-use vs the siblings get_fact_changes and search_hotels. Usage is implied rather than spelled out.

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 no annotations, the description carries the full behavioral burden, and it mostly does not. 'Facts are cited' hints at output provenance, but nothing is said about permissions, result format, ranking/relevance behavior, or pagination. 'precision is null' is unexplained and conveys no actionable behavior.

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 with the core purpose, which is good. However, the dangling fragments 'Facts are cited' and 'precision is null' consume space without earning their place and break the structure.

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 3-parameter search tool with no annotations and no output schema, the description covers the core handoff to get_hotel_facts but leaves result format, limit semantics, and region semantics unstated. It is adequate but has visible gaps given the absence of any supporting structured metadata.

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 33% (only query is documented). The description partly compensates by enumerating the kinds of values query accepts and by giving region examples (Algarve, Lisbon coast, Costa de la Luz), but the limit parameter and its 1-20 bound are never explained anywhere, 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 opening clause gives a specific verb (Find) plus the resource (hotels) and the searchable keys (name, town, domain, register id), and it explicitly separates this tool from the sibling get_hotel_facts, which takes the property_id. The trailing fragments ('Facts are cited', 'precision is null') add noise rather than clarity, keeping it just 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?

It gives a concrete workflow: this tool locates hotels, then you pass the resulting property_id to get_hotel_facts. That is clear context for selecting the tool, though there is no explicit when-not guidance or mention of get_fact_changes.

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