ApiFlash MCP by usefulapi

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), disclosing quota accounting per capture, the cache/free-replay rule, the 4 MB image cap with link fallback, and that the returned cache link requires the user's own access key and is therefore not shareable. These are operationally decisive facts an agent could not infer from annotations.

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?

Front-loaded with purpose and return behavior, then quota, then options, then the endpoint. Dense but every sentence carries information; the enumerated option list is the only slightly expendable portion.

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 27-parameter, no-output-schema capture tool, the description covers the essentials an agent needs: return form and size limits, link semantics, quota impact, caching behavior, and the sibling for text extraction.

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 27 parameters including ttl, fresh, and the extract_* link outputs. The description's option inventory (format, viewport, wait conditions, etc.) largely restates what the schema says, adding only light grouping rather than new parameter meaning.

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 ('Capture a screenshot of a public web page') and specifies the underlying engine (ApiFlash headless Chrome) and return type (image up to 4 MB, or a link for larger). It also distinguishes itself from the sibling by naming apiflash_extract_page_content for reading extracted text.

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?

Gives concrete usage conditions around quota and caching (identical options within ttl are free, fresh=true always counts) and explicitly routes text reading to apiflash_extract_page_content. It does not, however, state when-not to use this tool or contrast it with apiflash_get_quota.

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?

Goes well beyond the annotations by disclosing quota accounting per capture, cache-hit conditions via ttl, the 30000-character truncation of returned content, and that the screenshot link requires the caller's own access key. It also flags the prompt-injection risk of third-party page text, which is exactly the kind of safety context annotations cannot express.

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 dense sentences, front-loaded with what is captured and returned before cost and safety caveats. The trailing raw endpoint string ('GET /urltoimage?response_type=json&extract_text=true') is redundant noise that a tool caller cannot use directly.

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 return-value burden and does: text or HTML truncated at 30000 characters plus a screenshot cache link with an access-key caveat. Quota, caching, timeout-adjacent waiting, and untrusted-content handling are all covered for a 9-parameter 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?

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter behavior the schema cannot: the interaction between ttl, fresh and quota cost, plus the text-default and 30000-char cap on the content parameter.

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 ('Capture a public web page ... return its extracted text (default) or HTML') and names the exact payload shapes, which separates it cleanly from apiflash_capture_screenshot. The output modalities (text/HTML plus a screenshot cache link) are explicit.

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?

Gives clear context for when a fresh capture is worth it (ttl-cached repeats are free, fresh=true always costs) and warns that the page content is untrusted. It never explicitly states the alternative sibling to use when an actual image is wanted, so routing versus apiflash_capture_screenshot is left 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 cover the safety profile (readOnly, idempotent, closed-world), so the bar is lower. The description adds genuinely useful behavior: this call costs nothing and does not consume a screenshot credit, plus the underlying endpoint GET /urltoimage/quota. That is real value beyond the structured fields.

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 short sentences, zero waste. The quota description comes first, the cost-free reassurance second, and the endpoint path last as a compact reference.

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 compensates by naming the returned fields (limit, remaining, reset time in UTC). For a zero-parameter, read-only tool this covers everything an agent needs to call it correctly and 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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description does not need to explain syntax for a no-argument call.

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+resource (get ApiFlash screenshot quota for the current billing period) and enumerates exactly what comes back: limit, remaining, reset time. This is clearly distinguishable from the sibling capture_screenshot and extract_page_content tools, which act on pages rather than account state.

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 when to call it (checking remaining capacity before spending credits) via 'Free: this call does not use a screenshot', but never states that explicitly or routes the agent to alternatives. Usage context is inferable rather than spelled out.

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