Pacific/Apia clock

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only says 'HEAD a public URL and return status only' – it does not reveal that most parameters are 'discarded' or that some involve no network access (path), nor does it mention potential side effects or response format. This is severely under-disclosed for a tool with 9 parameters.

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 with no wasted words, but it is under-specified rather than appropriately concise. It front-loads the core action but omits essential context about the parameter set and tool scope, making it structurally incomplete.

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 9 optional parameters and no output schema, the description is grossly incomplete. It fails to explain the purpose of most parameters, the tool's relationship to sibling tools, or what 'status' means. An agent cannot reliably select or invoke this tool based on the current description.

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 descriptions cover 100% of parameters, providing individual semantics (e.g., 'discarded after the shape check'). The description itself adds no parameter-specific meaning, which is acceptable given the high schema coverage. Baseline 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 states a clear verb ('HEAD') and resource ('public URL') with a specific output ('status only'), but it does not distinguish this tool from siblings like browser-url-ok or playwright-url-ok that also check URL health. It also ignores the 8 other parameters (city, feed, json, etc.), which suggest a broader purpose, creating ambiguity about what the tool actually does.

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 mention of when to use this tool versus alternatives, nor any exclusion criteria. The description gives no context about suitable use cases or when another sibling (e.g., normalize-url for normalization, web-fetch for full content) should be preferred.

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?

No annotations are present, so the description carries the full burden. It only says 'Path discarded', which hints at one behavior but does not explain what happens to the other parameters, what the tool returns, whether it has side effects, or what constitutes a valid Figma URL shape. This is almost completely opaque for a tool that appears to be a shape checker.

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, which is concise, but it is under-specified rather than appropriately concise. It omits critical information that would justify its brevity. The 'Path discarded' clause is cryptic and does not earn its place without context.

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 9 optional parameters, no output schema, and no annotations, the description is severely incomplete. It does not explain what 'parse' returns, how to interpret the shape check, or why the other parameters exist. An agent cannot safely invoke this tool based on the description alone.

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 each parameter has some text, but the descriptions are generic and many say 'discarded'. The description itself does not mention the 'url' parameter or indicate which of the 9 parameters is relevant to the Figma URL task. It adds no clarity beyond the schema, and the schema's own descriptions are unhelpful for distinguishing which input matters (e.g., 'HTTPS URL to normalize or cite' is ambiguous).

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 verb ('Parse') and a resource ('Figma file URL'), which is a start, but it is extremely vague. It does not clarify what 'parse' means (validate, normalize, extract components?) or which input parameter is the intended target. The schema lists 9 unrelated parameters (city, feed, json, etc.) with no indication of how they relate to a Figma URL, so the agent cannot confidently infer the tool's actual scope. It also fails to distinguish this tool from siblings like 'normalize-url' or 'browser-url-ok'.

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?

No guidance is provided on when to use this tool versus alternatives. There is no mention of conditions, prerequisites, or when not to use it. Given the sibling tools for shape-checking various URL types, the agent is left to guess whether this applies to Figma URLs specifically or all URLs.

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 of behavioral disclosure. It does state 'No disk access,' which is a useful safety trait, but it says nothing about what happens with the other parameters, whether they are validated, what the return format is, or whether multiple inputs are accepted. For a tool with no annotations and 9 params, this is insufficient.

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 extremely short, but it is under-specified rather than concise. For a tool with 9 parameters and no other context, two sentences are not enough. It fails to front-load any usage or scope information that would help an agent.

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?

Given the high parameter count, no required params, no output schema, and no annotations, the description is severely incomplete. An agent cannot infer how to call this tool correctly, what the expected output is, or whether to pass one param or many. The tool appears to be a catch-all validator, but the description hides that.

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% because each parameter has a description. The description itself adds no meaning beyond the schema; it only repeats the path focus. The schema descriptions provide basic semantics (e.g., 'discarded after the shape check'), so the baseline of 3 is appropriate since the schema carries the load.

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: 'Check whether a path looks safe.' However, it ignores the other 8 input parameters (ref, url, city, feed, host, json, zone, query), which suggests the tool actually handles multiple types of shape/validation checks. This partial scoping is misleading and does not distinguish it from sibling shape-check tools like domain-shape or figma-url-shape.

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?

No guidance on when to use this tool versus alternatives. The description does not mention any conditions, exclusions, or sibling tools. An agent has no way to know whether to pick file-path-ok over wiki-title-ok or validate-json.

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 of behavioral disclosure. It only states the purpose, omitting details about network access, whether the tool is read-only, what it returns, or side effects. The schema mentions 'discarded after the call' for some params, but that is not in the description.

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, which is concise, but it is under-specified for a tool with 9 parameters and no annotations. It lacks any structure or front-loading of critical usage information, making it insufficient rather than appropriately concise.

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 9 optional parameters, no annotations, and no output schema, the description is severely incomplete. It does not explain how to request lat/long, what input format is expected, or what the result looks like. An agent cannot correctly invoke this tool based on the description alone.

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 provides descriptions for all 9 parameters (100% coverage), so the baseline is 3. The description adds no parameter-specific semantics beyond the schema, and the schema itself is confusing (e.g., 'city' is described as a 'public weather hint' rather than a geocoding input).

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 provides latitude and longitude for a place using Open-Meteo, giving a specific resource and external service. However, it does not differentiate it from sibling tools like weather-hint or timezone, and the input schema includes many seemingly unrelated parameters (ref, url, json, path) that confuse the intended use.

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?

No guidance is provided about when to use this tool versus alternatives. The description does not mention which parameter (e.g., city) is the primary input, nor does it contrast with sibling tools like weather-hint or geo-related tools. An agent would have no basis for selecting this over other hints.

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?

No annotations are provided, so the description carries the full burden of disclosing behavioral traits. The description does not state whether the tool is read-only, what it returns, whether it has side effects, or any constraints. For a tool with 9 parameters and no output schema, this is a critical omission.

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 short sentence, which is concise in length but under-specified. It lacks the essential details needed to understand the tool's function, making it an under-specification rather than effective conciseness. It does not earn its place because it fails to convey the core action.

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 9 parameters, no required fields, no output schema, and no annotations, the description is extremely incomplete. An agent cannot determine what the tool does, what inputs it expects, or what outputs it produces. The lack of any behavioral or usage detail makes it nearly unusable without external knowledge.

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 covers 100% of parameters, so the baseline is 3. However, the description adds no information about which parameters are relevant or how they relate to the tool's purpose. The schema descriptions are clear individually, but the tool description does not guide the agent on selecting the appropriate parameter, which is a missed opportunity.

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 resource ('Common IANA timezone names') and a context ('for clock calls'), but it does not specify an action or verb. It is unclear whether the tool lists, validates, filters, or returns timezone names. This is not a tautology but remains vague and does not differentiate it from siblings like 'timezone' or 'utc-time'.

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 phrase 'for clock calls' implies a usage context, but there is no explicit statement about when to use this tool versus alternatives such as 'timezone', 'tz-pacific-apia', or 'utc-time'. No exclusions or selection criteria are provided, leaving the agent to infer the tool's role.

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 full behavioral burden. It claims a network fetch and return of group counts but does not disclose side effects, failure behavior, or what 'group counts' means. The parameter descriptions in the schema repeatedly state 'discarded after the check', implying the tool is actually a shape checker, which contradicts the stated robots.txt fetching purpose. This inconsistency is significant.

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, extremely concise and front-loaded. It does not waste words. However, the brevity contributes to under-specification, so it is not a full 5, but it earns points for being short and direct.

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?

Given the tool has 9 parameters, no output schema, and no annotations, the description is grossly inadequate. It does not explain the relationship between the parameters and the operation, the format of the output, error conditions, or the meaning of 'group counts'. The mismatch with schema parameter descriptions makes the tool nearly impossible to use 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 no value for parameter understanding. More critically, the schema parameter descriptions (e.g., 'discarded after the shape check') suggest a different tool behavior than the description's robots.txt fetch, actively confusing the agent rather than clarifying parameter roles. The description fails to compensate for the mismatch.

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 action: fetch a public robots.txt and return group counts. However, the 9 input parameters are entirely generic and do not clearly map to this purpose (e.g., 'city', 'json', 'zone'). The description does not explain how the parameters relate to fetching robots.txt, so an agent cannot confidently select or invoke the tool based on this alone.

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?

No guidance is provided on when to use this tool versus the many shape-checking siblings (e.g., domain-shape, github-repo-shape). The description does not mention any conditions, prerequisites, or alternatives, leaving the agent to guess based solely on the name.

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 full responsibility for behavioral disclosure. It states 'Key discarded,' which is a transparency note about side effects, but it doesn't explain what happens on success/failure, whether the tool makes network calls, or what output the caller receives. The tool's behavior beyond the discard note is opaque.

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 very short, two sentences, with no fluff. It front-loads the core purpose and includes a side-effect note. However, the brevity comes at the cost of essential information, so while it is concise, it is under-specified.

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 tool has 9 optional parameters, no output schema, and no annotations, yet the description provides almost no context. It doesn't specify which parameter holds the Jira key, what 'shape' means (regex, format), or what the return value indicates. An agent cannot correctly invoke this tool based on the given information, making it critically incomplete.

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 covers 100% of parameters, so the baseline is 3, but the description fails to connect any parameter to the Jira key. The schema descriptions are generic (e.g., 'Git ref name; discarded after the shape check') and none explicitly refers to a Jira issue key. The description adds no meaning to help an agent select the correct parameter, making the tool essentially unusable without prior knowledge.

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 action: 'Check a Jira issue key shape.' It uses a specific verb and resource, and the phrase 'Key discarded' indicates the tool does nothing else. It is distinguishable from siblings like domain-shape or github-repo-shape by the Jira focus, though it doesn't explicitly name 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?

There is no guidance on when to use this tool versus alternatives. It doesn't mention conditions like 'for Jira issue keys, use this' or exclude cases like non-Jira keys. An agent has to infer usage from the name alone, which is insufficient given the generic parameter list.

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?

No annotations are provided, so the description must carry the behavioral burden. It discloses that no browser is launched, which is a useful negative behavior, but it fails to explain that many parameters are discarded (e.g., 'city', 'zone', 'query') or that the tool appears to perform shape checks. There's no mention of side effects, auth, or limitations. The description is too thin for a tool with 9 optional parameters.

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 concise — two short sentences — and not bloated. However, it omits crucial context and doesn't structure information logically. It's appropriately sized but under-specified, so it earns a middle score.

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 9 optional parameters, no required ones, and no output schema, the description should clarify the role of each parameter and what the tool returns. It does neither. The description doesn't explain how the URL is validated, what 'opened' means, or how the other parameters fit in. An agent cannot reliably invoke this tool correctly based on the given information.

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 has 100% coverage with per-parameter descriptions, but those descriptions are confusing and often irrelevant to the stated purpose (e.g., 'city' for weather, 'zone' for timezone). The tool description adds no parameter information, and the schema descriptions themselves contradict the tool's focus on URL checking. Baseline for high coverage is 3, but the contradictory and irrelevant parameter descriptions reduce the 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?

The description states a specific action — 'check whether a URL can be opened' — and adds a key differentiator: 'No browser is launched.' This distinguishes it from browser-launching tools like browser-url-ok, though it doesn't explicitly name alternatives. The verb+resource is clear, but it could be more explicit about why this tool exists vs. siblings.

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 no guidance on when to use this tool versus alternatives. It doesn't mention scenarios, exclusions, or contexts where this tool is preferred. With siblings like browser-url-ok, normalize-url, and web-fetch, the agent has no basis for selecting this one.

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?

No annotations are provided, so the description must fully disclose behavior. It only states 'Current time' implying a read-only operation, but does not mention that the schema includes many irrelevant parameters that are discarded or ignored. This omission is a significant behavioral gap that could confuse an agent into thinking other parameters matter.

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, efficient sentence that is front-loaded with the core action. It contains no fluff, but also omits necessary clarifying details about the parameters and scope.

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?

Given the complexity of the schema (9 params, only 1 relevant), the description is incomplete. It does not specify the output format, mention that only 'zone' is used, or explain the behavior of the other parameters. Without an output schema, the agent has no idea what to expect in return, and the presence of irrelevant params makes correct invocation ambiguous.

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?

While schema description coverage is 100%, the tool description adds no clarification about which parameter (zone) is the operative one. The schema itself includes nine parameters, many of which appear unrelated to timezone lookup (e.g., 'ref', 'url', 'city'), and the descriptions for those indicate they are discarded, but the tool description fails to highlight that only 'zone' is relevant. This leaves the agent uncertain about how to use the tool correctly.

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 returns the current time for a named IANA timezone, which is a specific verb-resource combination. It is distinguishable from siblings like 'utc-time' and 'iana-zones' in that it returns a time for a specific named zone, but it does not explicitly name those alternatives or contrast 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?

No guidance is given on when to use this tool versus alternatives like 'utc-time' or 'iana-zones'. The description does not mention conditions, exclusions, or preferred usage contexts. An agent must infer when to pick this over a sibling.

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 only states the output (current local time) and does not mention that the tool discards most parameters, is read-only, or how it handles the zone parameter. The behavior is essentially unspecified beyond a trivial one-liner.

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 with no wasted words, but it is under-specified rather than concise. It lacks necessary content to guide correct usage, so it does not earn its place as a complete description.

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 tool has 9 parameters, no output schema, and no annotations, making it complex. The description provides minimal information—no return format, no parameter guidance, no exclusions. This is completely inadequate for an agent to select and invoke the tool 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% with each parameter having a description, so a baseline of 3 is expected. However, the description fails to clarify which parameters are relevant to the tool's purpose. The description implies a fixed timezone (Pacific/Apia) while the schema includes a 'zone' parameter, creating ambiguity. The description adds no value beyond the schema and may confuse the agent.

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 returns the current local time for Pacific/Apia, a specific verb and resource. However, it does not differentiate from sibling time tools like 'timezone' or 'utc-time', and the schema includes many unrelated parameters that muddy the intended scope, so it is not fully distinct.

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 no guidance on when to use this tool versus alternatives. There is no mention of context, exclusions, or prerequisites. The agent is left to guess which of the 9 parameters are relevant and how this tool differs from other time-related 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, the description carries full responsibility for disclosing behavior. It only says 'Current temperature' which implies a read-only action, but it doesn't explain that other parameters are discarded or that the tool performs other checks (as hinted by schema descriptions like 'discarded after the shape check'). The description doesn't reveal the multi-purpose nature or any side effects, leaving the agent uncertain about what happens when other parameters are provided.

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, which is concise, but it under-specifies the tool's behavior. It lacks structure and doesn't front-load critical disambiguation. It is more under-specified than genuinely concise, as it omits necessary context.

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?

Given the tool has 9 parameters, no output schema, and no annotations, the description is severely incomplete. It doesn't explain the full set of operations, the return format, or how to handle multiple parameters. An agent cannot correctly invoke this tool for anything beyond the trivial city-temperature case, and even that lacks detail like units or API specifics.

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?

While schema coverage is 100%, the description adds no value for parameters beyond mentioning 'city'. It doesn't clarify which parameters are relevant for the weather function or how the others are handled. The description fails to compensate for the confusion caused by the many optional parameters, so it doesn't help the agent decide what to provide.

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 clear purpose for the weather use case: 'Current temperature for a city via Open-Meteo.' However, the schema includes 9 unrelated parameters (ref, url, feed, host, json, path, zone, query) that suggest the tool is multi-purpose, yet the description only covers one function. This makes the actual scope ambiguous and does not distinguish it from siblings like geo-hint or timezone.

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 provides no guidance on when to use this tool versus alternatives. It doesn't mention that it handles multiple hint types or specify conditions for selecting weather-hint over siblings like geo-hint or timezone. No exclusions or alternative routing is given.

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