iWonder

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

Annotations already declare readOnlyHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuine context beyond them: the exact payload contents and the fact that availability is a 'one-line summary' rather than full availability data. It does not mention behavior for unknown slugs or region-scoped deep 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?

Two tight sentences: the payload comes first, the optional-parameter effect second. No filler or repetition of 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?

With no output schema, the description carries the burden of describing return contents and does so field by field, including the conditional watch_summary. Only edge behavior (invalid slug, missing country) is unaddressed, which is minor for a read-only lookup.

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 both parameters (ISO alpha-2 country, slug-or-UUID) are already documented structurally. The description restates the country parameter's effect as a 'one-line availability summary' and adds no format detail for id_or_slug, so it meets but does not exceed the baseline.

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 — 'Full metadata for one documentary' — and enumerates the returned fields (synopsis, director, genres, topics, runtime, age rating, deep link), so an agent can tell this is the single-film detail lookup rather than a list. It never names search_documentaries or where_to_watch, so the separation from siblings is inferred rather than stated.

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 sentence about passing the country code to obtain an availability summary gives actionable conditional guidance for one parameter. There is no explicit statement of when to prefer where_to_watch for availability-only questions, nor any when-not guidance, leaving the overlap with the sibling to inference.

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, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine value by disclosing the return contents (availability status per title and deep links), which matters because there is no 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?

Three short sentences, front-loaded with purpose, then return shape, then the key parameter hint. Nothing is redundant, though the second and third sentences could be tightened into one.

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 10 parameters, no output schema and no explicit sibling routing, the description does well to cover the return payload but leaves filter semantics and pagination behavior unexplained. It is adequate, not complete, for a search tool of this surface area.

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 50% across 10 parameters; query, country, services, kids_mode and availability are already documented in the schema. The description only reinforces the country parameter's purpose, and says nothing about the undocumented filters (page, per_page, year_from, year_to, max_runtime_minutes) or how they compose.

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 names a specific verb and resource — 'Search the iWonder catalogue of documentaries' — and sketches the return shape (matching films, availability, deep links). It does not explicitly contrast with the siblings get_film and where_to_watch, so an agent must infer that this is the discovery entry point.

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 only usage instruction is 'Pass the viewer's two-letter country code to scope availability to their region,' which is parameter guidance rather than when-to-use guidance. There is no statement of when to choose this over get_film or where_to_watch, leaving that inference to the agent.

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 cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower; the description adds real behavioral context beyond them: the answer is geo-scoped, the call fails closed when country is missing, and the three availability categories that can come back. It stops short of noting caching or coverage limits per region.

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?

Effectively one compact sentence with the availability modes front-loaded and the critical country constraint trailing. No waste, though the interrogative framing is slightly less direct for an agent than an imperative statement would be.

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 only two required parameters, no nested objects, and no output schema, the description carries the needed burden: it explains what the answer means (free vs. subscription vs. external service) and the fail-closed behavior when country is absent. That substitutes well for a missing 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?

Schema coverage is 100% and both parameters are fully documented in the schema, so the baseline of 3 applies. The description's note that country is required and geo-scoped largely restates the schema's own parameter description rather than adding new semantics.

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 names the resource (documentary playability) and enumerates the answer modes the tool returns: free on iWonder, iWonder Plus subscription, or streaming services. It is phrased as a question rather than an explicit verb+resource statement, but an agent can still tell it apart from get_film (metadata) and search_documentaries (discovery) without opening the 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?

Usage is implied by the scenario ("can the viewer watch this in their country") and the hard constraint that a country is required and it fails closed without it. However, no sibling is named as an alternative and there is no explicit when-to-use/when-not statement distinguishing this from get_film.

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