Surt de Casa (surtdecasa.cat)

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

With no annotations, the description carries the transparency burdenates. 'Retorna' signals a read-only retrieval with no apparent side effects, and the description adds concrete behavioral detail: the source website and the included link and poster fields. It does not discuss output format or failure behavior, but for a zero-parameter fetch these are secondary concerns.

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 a single sentence that places the action and result first, then the source, then the output elements. Every phrase contributes meaning and there is no filler or repetition.

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 zero-argument tool with no output schema, the description is complete enough: it states what is returned, where the data comes from, and what each result includes. An agent has what it needs to decide whether to call the tool and to interpret the result.

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 input schema has no properties and schema coverage is 100%, so the baseline for a 0-parameter tool is 4. The description reinforces that the tool is an unparameterized weekly listing, which is sufficient.

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 uses a specific verb ('Retorna') and a concrete resource ('les pel·lícules de la setmana a surtdecasa.cat'), and it also states what each result contains: an enllaç and a cartell. This clearly differentiates it from generic siblings like cercar_agenda, though it does not explicitly contrast itself with them.

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 this is the tool for weekly cinema listings from surtdecasa.cat, but it does not state when to use it instead of alternatives or provide any exclusions. An agent has to infer the use case from the domain rather than from explicit 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?

With no annotations, the description carries the behavioral disclosure burden. It does add useful information such as support for pagination and a dd/mm/yyyy date format, but it does not mention result limits, default page, ordering, or the shape of the returned events.

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 only two sentences and front-loads the core purpose before summarizing the filter families and pagination. Every clause adds useful selection or invocation information; there is no filler.

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 tool with eight optional parameters, the fully documented schema plus this concise overview is mostly complete: the agent knows what the tool does, which filters exist, and that pagination is supported. It would be more complete with an explicit note about the result structure, but that is not a critical gap for invoking 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 description coverage is 100%, so the schema already documents all eight parameters. The description largely restates the filter types and enum categories without adding deeper parameter-level semantics, so the baseline score of 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?

The description opens with a specific action and resource: 'Cerca esdeveniments a l'agenda de surtdecasa.cat' and then enumerates the filter dimensions. It is clearly a search tool for agenda events, but it does not explicitly differentiate itself from siblings like cartellera or detall_esdeveniment.

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?

There is no guidance about when to choose this tool instead of cartellera or detall_esdeveniment, and no explicit exclusions or 'use this when' conditions. The text explains what the tool can filter by, but not when it is the right choice among siblings.

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 provided, the description carries the full burden. It discloses what the tool returns, which implies a read-only retrieval operation, but it does not explicitly state that the tool has no side effects or require authentication. Still, for a simple detail-fetching tool, 'Retorna' is reasonably transparent.

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 a single, front-loaded sentence that states the action, lists the returned content, and gives a necessary prerequisite. Every clause earns its place, and there is no verbose or redundant wording.

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?

This is a low-complexity tool with one parameter and no output schema, so the description is largely adequate. It covers what the tool returns, the required input, and where that input comes from. A clearer statement about output structure or read-only behavior would make it more complete, but nothing essential for calling 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?

The schema already documents the single 'url' parameter with a concrete example, giving 100% coverage. The description adds extra meaning by stating that the URL must come from cercar_agenda, which clarifies the parameter's expected provenance beyond the schema's format example.

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 clearly states the tool's function: 'Retorna tota la informació d'un esdeveniment de l'agenda' and enumerates the types of information returned (dates, place, towns, price, description, links). It also links its input to cercar_agenda, distinguishing it from the search tool, though it does not explicitly contrast with cartellera or poblacions.

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 gives a practical usage prerequisite: it requires the URL or path returned by cercar_agenda. This tells the agent that a search should happen first, providing clear context for when to invoke this tool. However, it does not explicitly state when not to use it or mention alternatives beyond the implicit connection to cercar_agenda.

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 provided, the description carries the full burden of behavioral disclosure. It states the input (prefix/fragment) and output (exact names), which is helpful, but it does not mention potential side effects, rate limits, result size limits, or error handling. For a simple autocomplete this is adequate but not rich.

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 two concise sentences that lead with the core purpose and then the input-output contract. Every word adds value; there is no filler or redundant explanation.

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 low-complexity tool with one parameter and no output schema, the description gives enough context: it defines what the tool does, what input it accepts, and how the results relate to another tool. The lack of explicit return-format details is a minor gap given the simplicity of the operation.

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 provides 100% coverage for the single parameter 'terme' with the description 'Prefix o fragment del nom de població'. The tool description adds only a restatement of the same concept ('Passa-hi un prefix o fragment de nom') without introducing new semantic detail, so it meets the baseline but does not exceed it.

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 clearly identifies the tool as an autocomplete for 'poblacions de surtdecasa.cat' and states exactly what it returns: the exact names accepted by the population filter of 'cercar_agenda'. This specific verb-plus-resource phrasing and the explicit connection to the sibling tool distinguish it from the other tools.

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 explains that the tool returns names accepted by the 'poblacio' filter of 'cercar_agenda', which indicates when this tool is useful: when populating that filter. It provides clear context and implies the workflow, though it does not explicitly state when not to use it or mention alternatives.

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