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

With no annotations, the description carries the full burden. It discloses the 'clean' action, that it returns 'clean text plus provenance', and the auto-read behavior. However, it lacks disclosure about edge cases (e.g., when no matching filing is found, or if both url and query are provided) and does not mention any potential rate limits or authorization requirements.

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, front-loaded with the core function, and includes an illustrative example without any filler. Every clause contributes essential information, making it highly efficiently structured.

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 no output schema and no annotations, the description covers the two usage modes, the return value (clean text plus provenance), and gives an example. It could further elaborate on what 'clean' entails or what 'provenance' includes, but it is sufficiently complete for the tool's moderate complexity.

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 describes all three parameters at 100% coverage, so the baseline is 3. The description adds meaningful context by explaining the OR relationship between url and query+formType, and provides a concrete example, which goes beyond the schema's individual property descriptions.

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 ('Fetch and clean') and the resource ('a specific SEC filing'). It also distinguishes from siblings like finance_filings by focusing on specific filing retrieval and mentioning the auto-read mode and provenance, making the tool's purpose unambiguous.

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 explicitly outlines two usage modes: pass a URL directly, or provide a company query plus formType to auto-read the most recent matching filing, with the example 'latest 10-K for NVDA'. This provides clear context on when to use each, but it does not explicitly mention alternatives or exclusions relative to sibling tools.

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 that the tool is 'Free, official, no API key', lists the exact returned fields (form type, dates, accession number, URL), and establishes authoritative provenance. It omits details like rate limits or error behavior, but for a read-only listing tool this is sufficient disclosure.

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, resource, query methods, and key value propositions (free, official, no API key) without wasted words. Every part contributes essential information.

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 no output schema and no annotations, the description is quite complete: it explains the purpose, input methods, output contents, and source reliability. It doesn't explicitly mention pagination or edge cases, but given the simplicity (3 params, one required) and the presence of a sibling read tool, coverage is adequate.

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. The tool description adds no new semantic information beyond the schema—it repeats the query types and implies recency, but the schema already documents ticker/name/CIK and limit. Baseline 3 is appropriate since the schema does the heavy lifting.

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 'List a company's recent SEC filings from EDGAR' with the query options (ticker, name, or CIK). This specific verb+resource combination distinguishes it from sibling tools like finance_filing_read (which reads a specific filing) and finance_financials (which likely fetches financial 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?

The description implies usage by specifying the listing function and output, but it does not explicitly state when to use this tool versus alternatives or mention exclusions. The mention of returning a 'direct document URL' hints at pairing with a read tool, but this is not made explicit.

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 adds valuable context by noting each figure is stamped with exact filing provenance and that no API key is required. It does not disclose potential limitations such as coverage gaps for non-XBRL filers or how recent the data is, but the provenance detail provides meaningful transparency.

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, front-loaded with the key financial outputs, followed by provenance and input details. Every sentence contributes essential information with no wasted words.

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 one-parameter tool with no output schema, the description covers the core aspects: what data is returned, provenance, accepted input types, and access requirements. It does not explicitly mention whether the result covers a single fiscal period or a range, but the essentials are sufficient for an agent to know what to expect.

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 fully documents the single 'query' parameter with a description covering ticker, company name, or CIK. The description repeats this information without adding further nuance, so it neither enhances nor detracts from the schema's already high coverage.

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 returning key structured financial metrics (revenue, net income, total assets, cash, diluted EPS) from SEC XBRL data, with authoritative provenance. It does not use an explicit verb like 'get' or 'retrieve', but the resource and scope are specific and distinguish it from sibling tools dealing with filings.

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 helpful usage context by stating accepted input types (ticker, name, CIK) and that no API key is needed. However, it does not explicitly compare this tool to siblings like finance_filings or finance_filing_read, so when to choose this over alternatives is implied rather than stated.

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 goes beyond a simple 'check' by revealing that it 'returns only what's new and rolls baselines forward'—a stateful side effect that is critical for an agent to understand. It also honestly notes the SEC filing index may lag up to ~1h (cache), setting correct expectations for freshness.

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 three sentences, each earning its place: the first states the function, the second explains the behavioral side effect, and the third gives usage guidance and a caveat. It is front-loaded with the core purpose and avoids any filler 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?

For a zero-parameter tool with no output schema, the description is remarkably complete. It covers what the tool does, what it returns ('only what's new'), when to use it (scheduled runs), and an important limitation (cache lag). No significant gaps remain for an agent to invoke it safely.

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 there is no parameter surface to document. The description adds context about what the tool checks (all watches, since last check), which leverages the input schema fully (100% coverage by virtue of being empty). This meets the baseline for a no-parameter tool.

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 the specific verb 'Check' and clearly identifies the resource ('every watch') and scope ('for changes since the last check'). It explicitly mentions what is checked (new SEC filings, changed page content) and contrasts with sibling tools like watch_manage, making its purpose unmistakable.

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 concrete guidance: 'Run it on a schedule (cron / scheduled agent) to turn veris into an alert feed.' This tells the agent when to use the tool. While it does not explicitly name alternatives or exclusions, the context is clear enough that an agent would not confuse it with web_search or finance_filings.

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 discloses important behavioral traits: 'Adding baselines current state' indicates that add sets a baseline and does not immediately report changes, and 'watched by content hash' explains the mechanism for URLs. It does not mention authorization, rate limits, or response formats, but the disclosed behaviors are significant beyond what the schema shows.

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 three sentences, with the action front-loaded in the first sentence. Each subsequent sentence adds essential context without redundancy, making it concise and well structured.

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 description covers the tool's domain, the two watch types, and the baseline behavior, which is adequate for a simple CRUD tool. However, it does not describe return values (e.g., what list returns or what add/remove return), and there is no output schema to compensate. Overall it is quite complete but not fully.

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 all parameters with descriptions, but the description elaborates on target by specifying that it can be a ticker/name/CIK or a URL, and clarifies that formType applies to filings watches. This adds contextual meaning beyond the schema, so a 4 is warranted.

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 begins with 'Add, remove, or list watches,' clearly stating the verb and resource. It further explains that watches can target SEC filings or URLs, and distinguishes itself from the sibling tool watch_check by noting that watch_check is used later to see what's new. This makes the purpose unmistakable and differentiates it from related 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 provides context on what kinds of targets are supported (ticker/name/CIK for filings, https:// URLs for content hash), and explicitly recommends using watch_check later to see changes. It does not enumerate alternative tools for other purposes, but the guidance for when to use this tool is clear. A 4 is appropriate because it lacks explicit 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?

With no annotations available, the description carries the burden. It discloses the output (clean markdown plus provenance details) and the core value, but does not address error behavior, redirects, rate limits, or limitations. It is adequate but not deeply 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?

Two sentences, front-loaded with the main action, and each word adds value. No fluff.

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 two parameters, no output schema, and no annotations, the description covers the core functionality and unique value proposition well. It could be slightly more complete by noting error scenarios or typical use cases, but it is largely sufficient.

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 both parameters (url and fresh). The description adds no new parameter-specific meaning beyond the schema, so the 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 uses the specific verb 'Fetch' with a clear resource ('a URL') and emphasizes the provenance-tracking distinction, which sets it apart from siblings like web_search and web_research.

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 context is clear: use when you have a URL and want clean markdown with verifiable provenance. It doesn't explicitly mention alternatives, but the purpose is unambiguous. No exclusions are stated.

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 convey behavioral traits. It discloses the pipeline (search, fetch, clean, provide provenance) and output nature. However, it leaves 'top results' ambiguous and does not mention potential latency, failure modes, or what 'clean content' entails.

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 deliver all key information: the action, the output, and the ideal use case. No redundant filler or restatement of the title.

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 no output schema, the description sufficiently explains the return value (clean content with provenance) and when to use it. It does not over-explain; the schema covers parameter details. Minor omissions about practical limitations are acceptable given the concise 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?

Both parameters are fully described in the schema (query and n with default 3). The description adds no parameter-specific meaning beyond the schema, so it only meets the baseline for high schema coverage.

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 a specific multi-step action: 'search the web, fetch the top results, and return their clean content bundled with full provenance per source.' It distinguishes the tool from siblings (web_search, web_read) by emphasizing the one-shot combined operation and citation-ready output.

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 clear use case: 'Ideal for grounding an answer with citations.' It implies when to use this tool over web_search/web_read (when both search and read are needed together), though it does not explicitly name alternatives 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?

With no annotations, the description discloses meaningful behavioral details: it returns structured JSON with a result shape, and it explains the dynamic backend selection (Brave vs DuckDuckGo) based on BRAVE_API_KEY. It does not mention rate limits, ordering nuances, or error behavior, but for a simple search tool this is useful transparency.

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 three short, front-loaded sentences with no filler. Each sentence contributes distinct value: purpose, output format, and backend behavior.

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 schema covers parameters; the description supplies output structure and environment-dependent behavior, which is enough to invoke the tool. Minor omissions like pagination or rate limits are not critical, but the absence of annotations and an output schema means return semantics rely on this 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 already fully documents both parameters (query required, n optional with constraints and default). The description does not add extra parameter-level detail beyond the schema, though it hints at the result count controlled by n. Baseline 3 is appropriate when schema coverage is complete.

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 'Search the web' and specifies the output as ranked results with title, url, snippet, establishing a distinct search-engine function. It does not explicitly contrast with sibling tools like web_read or web_research, but the return format makes the purpose unambiguous.

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 such as web_read or web_research. It focuses on operational behavior (engine selection) rather than suggesting context for use, leaving the agent to infer applicability from the tool's name.

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