AgentScrape

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

The description reveals that the session persists cookies and localStorage, indicating statefulness. However, it does not mention what the tool returns (e.g., session ID), any side effects, or whether creation is idempotent. With minimal annotations, the description could be more 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, concise sentence that front-loads key information. Every word is necessary and provides 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 one optional parameter and no output schema, the description is mostly complete. However, it could mention what the tool returns (e.g., a session ID) to fully inform the agent.

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% for the sole parameter (ttl_seconds), so the baseline is 3. The description does not elaborate on the parameter beyond the schema, adding no extra 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?

The description clearly states the verb 'Create', the resource 'a stateful browser session', and specifies key features (persists cookies and localStorage across multiple calls). It distinguishes itself from sibling tools like scrape_webpage or extract_structured_data by focusing on session lifecycle management.

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 use the tool: when you need persistent state across multiple scrape/workflow calls. However, it does not explicitly mention when not to use it or provide alternatives, which would strengthen 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?

The description implies a read-only operation (extract) but does not disclose rate limits, authentication needs, or behavior on failure. Annotations are minimal, so the description carries burden but lacks depth.

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?

One sentence efficiently covers the tool's purpose and output types. No extraneous words; front-loaded with the 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?

While the description lists extracted metadata types, it does not describe the output format or structure. For a tool with no output schema and low schema coverage, this is 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 single parameter 'url' is a string with no schema description. The tool description does not clarify expected format (e.g., HTTP/HTTPS) or any constraints, leaving ambiguity.

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 'Extract page metadata' and enumerates specific types (title, description, Open Graph, Twitter cards, JSON-LD, canonical URL, all meta tags), making it distinct from siblings like scrape_webpage or extract_structured_data.

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 such as scrape_webpage or extract_structured_data. Lacks context on appropriate scenarios or exclusions.

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 (readOnlyHint/destructiveHint) are provided, and the description does not disclose behavioral details such as API rate limits, auth requirements, or failure modes (e.g., dynamic content limitations).

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 concise sentence that front-loads the purpose, but it is too brief to cover essential details.

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 5 parameters and no output schema, the description is insufficient. It omits key context like the optional schema parameter's purpose in structuring output, the wait parameters, and what happens on extraction failure.

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 60%, but the description adds no meaning beyond the schema for the described parameters. The wait_ms and wait_for parameters are undocumented in both schema and description, and the description does not compensate for these gaps.

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 extracts structured data from any webpage using natural language and returns JSON, distinguishing it from siblings like scrape_webpage (raw content) and extract_metadata (metadata only).

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 like scrape_webpage or extract_metadata. The agent is not told about prerequisites or exclusions.

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 lack behavioral hints (e.g., readOnly, destructiveHint). The description only mentions 'atomically' but fails to disclose side effects like state changes, error handling, or permission requirements, which is critical for a potentially destructive tool.

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 front-loads the core concept and lists actions. It is concise with no redundancy, though a structured list could improve readability.

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 parameters, multiple action types, no output schema), the description is too high-level. It omits return values, error handling, step execution order, and guidance on when to use this composite tool over simpler siblings.

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 low (25%), and the description only adds 'Up to 20 steps' as a constraint. It does not explain individual step properties (action, selector, text), leaving the agent to infer usage from action names alone.

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 it executes a multi-step browser workflow atomically, listing typical actions like navigate, click, type, etc., which distinguishes it from single-action sibling tools such as scrape_webpage or screenshot_webpage. The 'Up to 20 steps' constraint adds specificity.

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 does not provide guidance on when to use this tool versus sibling tools, nor does it mention prerequisites like needing a browser session. The agent must infer context from the action list alone.

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 beyond title, the description adds the behavioral note 'pay-per-call', indicating cost. However, it omits other important traits like rate limits, authentication requirements, handling of dynamic content, or error responses. The description provides some value but is incomplete for a tool that fetches external web pages.

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 with two sentences: first states the core function and output formats, second highlights the cost model. No unnecessary words, 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?

Without an output schema, the description does not detail the structure of returned JSON or HTML. It also lacks information on error handling, page load limits, or dynamic content support. For a scraping tool, these are relevant gaps. However, the core functionality is covered adequately.

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 baseline is 3. The description does not add further meaning to individual parameters beyond what the schema already provides (e.g., 'url', 'format', 'wait_ms'). The pay-per-call note is relevant but not per-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?

The description clearly states the verb ('scrape'), the resource ('any webpage'), and the output formats ('markdown, html, text, or json'). It also highlights the pay-per-call model, distinguishing it from sibling tools like screenshot_webpage or extract_metadata which have different purposes.

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 a general scraping use case but does not explicitly guide when to use this tool over alternatives like extract_structured_data (for structured extraction) or screenshot_webpage (for visual capture). No exclusion criteria or alternative contexts are mentioned.

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?

The description discloses key behaviors: outputs PNG, supports viewport options and full-page mode. However, without annotations, it doesn't address potential side effects, limitations (e.g., dynamic content), or safety profile. Still sufficiently transparent for a read-like tool.

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?

One sentence, front-loaded with action, no redundant words. Efficient 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?

Despite low parameter coverage and no output schema, the description omits crucial details: output format beyond 'PNG' (e.g., base64 vs URL), how to handle wait_ms and wait_for, and any return structure. Incomplete for an agent to reliably use.

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 description adds meaning for viewport (enum values) and full_page ('full-page mode'), but wait_ms and wait_for are left unexplained. With 20% schema coverage, the description partially compensates but leaves gaps for two 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 captures a PNG screenshot of any webpage, with specific verb and resource. It implicitly distinguishes from sibling tools like scrape_webpage (text extraction) and create_browser_session (session management).

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 vs alternatives, no when-not scenarios, and no mention of prerequisites or context. The description only lists features without directing agent choice.

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