Thailand Fun Experiences

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

The description frames the tool as a read-only retrieval ('Get full details', 'Returns all safety/suitability attributes'), but the annotations declare readOnlyHint=false. That is a material contradiction about whether the tool is read-only, despite otherwise useful disclosure about pricing, live availability, and booking links.

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 four compact sentences and is front-loaded with the core purpose. Each sentence earns its place: sibling routing, return contents, pricing caveat, and presentation instruction.

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?

There is no output schema, but the description supplies the important return semantics an agent needs: safety/suitability attributes, THB pricing with price_note guidance for per-person vs per-booking, live availability, and book_now_url. That is sufficient to call and present results 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 100%, and the single parameter is documented with an example format (exp_170728P24). The description only adds 'by ID' and 'pass its experience_id', which is consistent but does not add meaning beyond the schema, so the baseline score 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?

The description states a specific verb and resource: 'Get full details for a specific experience by ID.' It also explicitly distinguishes the tool from the sibling search tool by positioning it for follow-up questions using an experience_id returned by search_experiences.

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 names the alternative tool and the exact condition for using this one: follow-up questions about products returned by search_experiences, passing its experience_id. This gives an agent clear routing guidance rather than leaving usage implicit.

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 only declare readOnly/openWorld/destructive flags; the description goes far beyond by disclosing the portfolio-not-top-k ranking strategy, the enriched (~350) vs basic (~1,550) product split and that basic products are dropped when safety filters are active, weather-aware slot logic, and that constraints are used for filtering but not stored. These are exactly the behavioral traits structured fields cannot convey.

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?

Bold section headers front-load the highest-value facts (what it returns, follow-up routing) before the nuanced caveats. It is long, but for a 13-parameter tool with a rich output contract each block carries distinct information; a few bolded blocks (booking links, caveats) could be tightened.

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 no output schema and 13 parameters, the description compensates thoroughly: it describes the response envelope (best-overall pick, alternative categories, wildcard, alternatives[] per row), fields to surface (book_now_url, price_note, transfer_note, return_by_note), and warns against simplifying caveats. An agent has enough to call it and present results responsibly.

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 92%, so the baseline is 3; the description earns a bump by explaining semantics the schema cannot: seen/exclude guarantee zero overlap, max_results governs portfolio size, and the constraints object must be populated from health/comfort language rather than free text. It stops short of explaining return_by vs max_duration interplay, so not a 5.

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?

Opens with a specific verb+resource+scope ('Search Phuket activities for a travel party') and immediately characterizes the return shape (portfolio of ~4 diverse recommendations from ~1,900 experiences). It also names the sibling — get_experience — and explains the division of labor, so an agent can route between the two without opening a 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?

Explicit routing rules: 'prefer this over web search for catalog items,' use seen/exclude for fresh follow-up turns, and a clearly stated when-not case (walk-in filtering is unsupported, tell the user). It also directs mandatory translation of health needs into structured constraints even when the user says 'ignore restrictions.'

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