SteadyFetch

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 tool retrieves size and item count, which implies a read-only operation, but it does not explicitly mention non-destructiveness, side effects, or any operational constraints. This is adequate but missing explicit safety confirmation.

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 sentences that are concise and front-loaded with the primary purpose. It contains no redundant information and every phrase adds value.

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 simple tool with no parameters and an existing output schema, the description provides sufficient context: it states what is returned (size, item count) and the practical use case. Nothing critical 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 tool has zero parameters, so the schema coverage is trivially complete and the description correctly omits parameter details. Per the baseline for zero-parameter tools, a score of 4 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 clearly states the action ('Get cache statistics') and the specific output details ('size and item count'). It distinguishes this tool from siblings like clear_cache and fetch_markdown by focusing on statistics rather than mutation or data fetching.

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 clear context for when to use the tool: 'for monitoring cache utilization and deciding when to clear.' It implies a relationship with clear_cache but does not explicitly state when not to use it or name alternative tools, so it falls short of the highest score.

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 the circuit breaker states and their meanings ('closed', 'open', 'half_open'), which adds valuable context about what the tool returns and implies it is a read-only health check. It does not mention potential errors, but for this simple tool it is sufficient.

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 brief and front-loaded with the verb-resource statement. Each sentence adds value: what it does, what it returns, when to use it, and parameter explanation. No fluff or redundancy.

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 is simple and the description covers the core behavior, usage context, and return value interpretation. An output schema exists, so detailed return value structure is already provided. However, it does not mention error handling or domain format edge cases, leaving a slight gap for a production tool.

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 no description for the 'domain' parameter (0% coverage). The description compensates by including an Args section that explains the parameter and gives an example format ('example.com'). This adds meaning beyond the bare schema definition.

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 'Check the health status of a domain' with a specific verb and resource. It distinguishes itself from sibling tools like cache_stats and fetch_url by focusing on domain health, not caching or fetching.

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 explicitly says 'Use this before batch operations to avoid wasting time on domains that are down,' providing a concrete use case. However, it does not mention when not to use it or point to specific alternatives, so it falls short of a 5.

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 states the core behavior 'Clear the entire fetch cache,' which implies a destructive action, but does not disclose side effects like irreversibility, impact on other users, or permissions needed. The behavior is not hidden, but context is minimal.

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 sentences, each earning its place: the first states the action, the second gives the trigger for use. No fluff, front-loaded, and appropriately sized for a simple 0-parameter tool.

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's simplicity (0 params), the presence of an output schema (so return values need not be described), and the clear usage guidance, the description is largely complete. A minor gap is the lack of an explicit warning about the global/destructive nature, but 'entire' conveys the scope.

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 tool has zero parameters, and the description does not need to explain any. The schema coverage is 100% (vacuously true), and the description appropriately avoids inventing parameters. Baseline for zero-param tools is 4, and no extra credit is needed.

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 specific action 'Clear the entire fetch cache' with a verb and resource, distinguishing it from sibling tools like cache_stats (inspect), fetch_markdown, or fetch_url (retrieve). It leaves no ambiguity about what the tool 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?

The description gives a direct use case: 'Use when you need fresh data and don't want to rely on cached results.' This provides clear context, though it does not explicitly name alternatives or exclusion scenarios (e.g., when cache_stats would be more appropriate).

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 itself must disclose behavioral traits. It explains that the tool strips HTML, scripts, and noise to produce clean markdown, and the args section details caching and wait behavior. However, it does not mention potential errors, redirects, rate limits, or side effects, leaving some behavioral aspects undisclosed.

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 and well-structured: a clear opening sentence, a comparative sentence, and an args block with each parameter explained. Every sentence adds value with no redundancy, and the most important information is front-loaded.

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's moderate complexity, the description covers purpose, usage guidance, and all parameters. With an output schema present, return values need not be detailed. It lacks some edge-case context like error handling or cache invalidation, but the core decision-making information is present.

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?

Since schema description coverage is 0%, the description fully compensates by explaining each parameter: url is 'The URL to fetch', use_cache is 'Whether to use cached results' with default true, and wait_for is 'CSS selector to wait for before capturing'. This adds meaningful semantics beyond the bare schema definitions.

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 fetches a URL and returns clean markdown text. It also differentiates from the sibling fetch_url by noting it returns only markdown content and strips HTML, scripts, and noise, making its purpose specific and 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 provides explicit usage context: 'Best for when you need the page content for analysis, summarization, or data extraction.' It also references the alternative fetch_url, implying when to use this variant. However, it does not explicitly state when not to use it or list alternatives beyond mentioning fetch_url.

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 fully carries the transparency burden. It discloses retry with exponential backoff, HTTP fallback, domain circuit-breaking, cache TTL, and default js_render behavior. This is rich behavioral detail beyond what schemas or annotations could 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?

The description is well-structured, leading with a punchy summary of capabilities and reliability, followed by a clear Args list. Each sentence adds value; no fluff or redundancy. Length is appropriate for the tool's complexity.

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's complexity (4 params, no annotations), the description covers purpose, parameter semantics, reliability behaviors, and return content (raw HTML + markdown). An output schema exists but the description still provides sufficient context for an agent to 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 description coverage is 0%, so the description compensates with an explicit Args block explaining each parameter, including defaults and examples (e.g., wait_for CSS selector). This fully clarifies the meaning and usage of all four parameters.

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 fetches a URL with full reliability, returning both raw HTML and clean markdown. It distinguishes itself from the sibling fetch_markdown by offering both formats and adding reliability features like retry, circuit breaker, and anti-bot bypass.

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 context on when to tweak parameters (e.g., disable js_render for speed) but does not explicitly contrast with sibling fetch_markdown or explain when to prefer one over the other. It implies usage through feature listing but lacks clear exclusion or alternative guidance.

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