takedown

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

The description adds meaningful behavioral context beyond the readOnlyHint annotation: it reiterates that the operation is read-only, clarifies that it does not judge the claim's merits, and states that it files nothing. It also discloses the output includes legal caveats, going beyond what annotations alone imply. No contradiction.

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 carrying substantive information: core purpose, output scope, and usage boundaries. It is front-loaded with the main verb and resource, 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?

With an output schema present, the description doesn't need to detail return values. It nonetheless outlines the major output categories (recipient, documents, process, caveats) and behavioral limits. This is complete for a tool of this 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?

Schema coverage is 100% for both parameters. The description only mentions the URL ('for this URL') and implicitly acknowledges the 'what' parameter by saying it is 'echoed into the plan, not judged.' This adds minimal value beyond the schema, so a baseline score 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 clearly states the tool's function: assess how a takedown for a URL would proceed. It enumerates specific outputs (where notice goes, documents, process, legal caveats) and distinguishes itself from siblings by noting it files nothing and defers to resolve_host for hosting-only questions.

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 provides when-to-use guidance ('Assess how a takedown for this URL would proceed') and when-not-to-use guidance ('does not judge the merits... files nothing'). It also names an alternative: 'Use resolve_host first if you only need the hosting answer.' This fully meets the criteria.

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 adds substantial behavioral context beyond annotations: email delivery, ~2 min duration, rate limits (3/day, 10/month), content captured, and lawful use. No contradictions with 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?

The description is concise (3 sentences), front-loaded with key action, and each sentence provides essential information without unnecessary detail.

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 (4 params, output schema, annotations), the description covers purpose, usage, behavioral traits, constraints, and delivery mechanism comprehensively. Output schema handles return value details.

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 good parameter descriptions. The tool description reinforces that email must be the user's own but adds little additional meaning beyond schema. Baseline 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 clearly states the tool preserves a public web page as forensic evidence, listing specific outputs and use cases. It distinguishes from siblings (assess_takedown, resolve_host, start_takedown) by focusing solely on evidence capture.

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 tells when to use ('save proof', 'screenshot for court', fix scam pages) and provides exclusion (lawful preservation only, public pages only). It does not directly name sibling alternatives but context implies appropriate use.

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?

Beyond the readOnlyHint annotation, it adds 'Read-only; files nothing' and 'A lookup, not legal advice; it does not guarantee removal'. It also discloses distinct behavior for direct hosts vs proxied domains, giving the agent robust expectations about results and 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 front-loaded with the primary purpose and each sentence contributes unique value: scope, specific identifiers, behavior variations, and caveats. It is detailed yet concise, 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?

Given that an output schema exists and annotations already declare read-only and open-world nature, the description sufficiently covers purpose, behavior, and limitations. It also addresses edge cases (proxied vs direct hosts) and sets expectations, making it complete for the tool's 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 input schema fully describes the only parameter 'url' as 'The infringing URL or bare domain' (100% coverage). The description does not add details about URL format or examples, so it adds no semantic value beyond the schema. Baseline 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 opens with the specific verb-resource pair 'Look up who hosts a URL and where an abuse/takedown notice would go', making the tool's purpose immediately clear. It further specifies outputs (CDN/proxy, platform, direct host, abuse contact), distinguishing it from action-oriented siblings like 'start_takedown' and 'preserve_evidence'.

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 for when to use this lookup tool versus proceeding to a takedown: it explains that for proxied domains it states that revealing the true host requires initiating an abuse report, implying a next step. However, it does not explicitly name alternatives or provide clear 'when not to use' 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?

Annotations only provide readOnlyHint and openWorldHint, so the description carries the burden of explaining behavior. It adds rich process details: the one-time human authorization step, what to prepare, what happens next, that it creates nothing by itself, and intake filtering. This aligns with the readOnlyHint and adds meaningful context beyond 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?

Three focused sentences, front-loaded with the main purpose. Every sentence adds value: process explanation, prerequisites, return contents, and intake exclusions. No redundancy or filler.

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 process, prerequisites, expected outcome (link plus preparation/next steps), and intake exclusions. An output schema exists, so return values need not be detailed here. For a one-parameter tool with strong annotations, this is complete.

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 already fully documents the single required 'url' parameter with a clear description ('The infringing URL or bare domain'), and schema description coverage is 100%. The tool description does not add further parameter-level detail, so the baseline of 3 applies.

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 a specific verb ('Get the secure onboarding link') and names the resource (takedown). It clearly distinguishes this tool from siblings like assess_takedown and preserve_evidence by framing it as the initiation/onboarding step, not the assessment or evidence-preservation step.

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?

Clear context is provided: use when ready to actually start a takedown and need the onboarding link. It states prerequisites (content owner opens link, signs authorization, proves ownership) and an exclusion (filings targeting lawful criticism, reviews, or journalism are declined). However, it does not explicitly name alternative sibling tools for when to use them instead.

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