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

With no annotations, the description carries the burden and is fairly transparent: it states zero cloud LLM token cost, an output size, and a compression ratio. It does not disclose edge-case behavior or detailed return structure, but the core behavior is clearly conveyed.

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 concise sentences, front-loaded with the core purpose and followed by concrete performance traits. No 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?

For a two-parameter tool with no output schema, the description tells the agent what it produces, roughly how much output to expect, and why it is cheap. It could specify the output shape more precisely, but nothing critical is missing for selecting and invoking it.

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 schema already documents raw_text and max_keywords. The description adds general context about entity/metric/keyword extraction but adds little parameter-level detail beyond what the schema provides.

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 names a specific verb ('distills'), a clear resource ('raw text'), and the outputs (entities, numerical metrics, salient keywords). It also quantifies compression, making it easy to distinguish from sibling text utilities such as extract_markdown or sanitize_pii.

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 doesn't name alternatives, but it communicates a clear use context: low-cost/zero LLM-token local distillation of long text. This is enough for an agent to select it over lookup/verify/sanitize tools, though explicit when-not guidance is absent.

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 at all, the description carries the behavioral burden and mostly meets it: it discloses that content is stripped (boilerplate, scripts, ads, navigation chrome) and that output is token-efficient Markdown. It does not cover failure modes, rate limits, or precedence when both url and raw_html are supplied.

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 short sentences lead with the core definition and immediately provide the key transformation detail. The 80–95% token-reduction claim adds value for an LLM-context tool and no sentence is redundant.

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 plus a fully documented schema is adequate for basic invocation, but with no output schema and no annotations it leaves some gaps: the exact return format is only implied as Markdown, and there is no guidance on error cases or how distill_context is different. A small note on precedence/edge cases would round it out.

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 url, raw_html, and include_links. The description adds no parameter-level detail beyond restating that the tool scrapes URLs or parses raw HTML, so it stays at the baseline 3.

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 a concrete noun phrase, “Web-to-Markdown context compressor,” and specifies the exact action: scraping URLs or parsing raw HTML into Markdown. It is clear about the resource and output, though it does not explicitly differentiate itself from the sibling tool distill_context.

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 context: whenever a web URL or raw HTML needs to be compressed into token-efficient Markdown. It does not provide explicit exclusions or name alternatives like distill_context, but the input domain is specific enough to guide selection.

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, and it does disclose meaningful behavior: it performs multiple lookup types and promises sub-5ms latency. It does not mention error handling, return structure, or any caveats, but for a read-only lookup tool the disclosed behavior is reasonably informative.

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 dense sentence that front-loads the core purpose and then lists specific resolution capabilities and a performance characteristic. Every clause adds useful information without 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 simple one-parameter lookup tool with no output schema, the description covers the main invocation context well: what input is needed and what kinds of results to expect. It stops short of describing the exact response shape or failure behavior, but the simplicity of the tool makes this a minor omission.

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 provides 100% coverage by describing 'ip' as an 'IPv4 or IPv6 address string to inspect.' The tool description adds no new parameter-level meaning, so the 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 uses a specific verb-resource pairing: it 'resolves IP routing taxonomy, private/loopback/bogon CIDRs, and performs reverse DNS PTR lookups.' This clearly differentiates lookup_ip from the text/email-focused sibling tools and states the function with concrete examples.

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 clear context for when to use the tool: whenever IP taxonomy, special CIDR classification, or reverse DNS information is needed. It does not explicitly name alternatives or exclusions, but no sibling tool overlaps with IP lookup, so the lack of exclusion guidance is not a significant gap.

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 present, so the description carries the full disclosure burden. It does disclose the exact repair behaviors (code fences, single quotes, trailing commas, Python literals) and a performance claim, but it is silent on the critical failure mode: what happens when the input cannot be repaired (throw, return original, return null). For a tool whose inputs are by definition malformed, this is a meaningful gap.

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 with the purpose front-loaded in the first line; the second sentence adds concrete specifics and the output standard. Efficient overall, though the 'sub-millisecond edge time' performance claim is the least decision-relevant detail and is slightly awkward phrasing.

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 one-parameter tool the description covers purpose, transformations, and the output standard, but with no output schema and no statement about error or fallback behavior, the agent is left guessing about the return shape and unrepairable-input handling. The phrase 'into valid RFC 8259 JSON' hints the output is a string, but it is not explicit.

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 single parameter raw_json, so the baseline is 3. The description adds genuine domain context beyond the schema's minimal 'Malformed or broken JSON string' by specifying the expected malformation classes (LLM artifacts like code fences, single quotes, Python literals), which helps an agent decide whether its input qualifies for this 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 names a clear verb+resource pair (repairs/fixes malformed JSON) and enumerates the specific transformations: stripping markdown code blocks, single quotes, trailing commas, and Python literals, with a compliance target of RFC 8259. None of the sibling tools (extract_markdown, lookup_ip, sanitize_pii, distill_context, verify_email) overlap with JSON repair, so it naturally stands apart.

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 phrase 'emitted by LLMs' establishes the intended input source, so an agent can infer the use case, but the description never explicitly states when to use this tool or when not to (e.g., input that is already valid JSON or non-JSON text). No alternative is named, though the siblings are all non-overlapping, so routing confusion is low.

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 behavior disclosure. It discloses the input (text) and the masking behavior for specific PII categories, but does not specify the output format, whether the entire text is returned, how masked placeholders look, or how toxicity filtering is handled despite being mentioned in the first sentence.

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 short sentences, front-loaded with the tool's core role and immediately followed by concrete PII examples and compliance purpose. No filler or redundant restatement of the tool name.

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 single-parameter tool with no output schema, the description is largely sufficient: it tells an agent what input to provide and why. Minor gaps remain, such as the exact masking representation and whether non-PII text passes through unchanged, but these do not block correct invocation.

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 the only parameter 'text' as 'Sensitive input text string to sanitize' with 100% coverage. The description adds context about what types of PII get masked, but does not add significant parameter-level detail beyond the schema, so the 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 identifies the tool as a PII redactor that masks specific PII types (emails, phone numbers, credit card numbers, SSNs) from text, and positions it as a privacy/compliance safeguard for external LLM calls. This distinguishes it sharply from sibling text tools like extract_markdown or repair_json.

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 states the contextual trigger: use this tool before sending data to external public LLMs, and names the compliance concerns it enforces (GDPR, HIPAA, DLP). It does not explicitly compare against alternatives or state when not to use it, but the use case is clear enough.

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 is the only source of behavioral information. It does disclose that MX checking is 'live' and lists concrete verifications (syntax, disposable domains, reputation), implying network dependency. However, it omits potential side effects such as latency, whether any email is sent, or failure/timeout behavior.

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, information-dense sentence that front-loads the tool's purpose and then lists differentiating capabilities. Every phrase carries weight, with no filler or redundant restatement of the tool name.

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 main verification steps but, since there is no output schema, it does not explain what the tool returns (e.g., a boolean, a score, or a structured report). It also lacks guidance on error handling, timeout behavior, or the impact of the live DNS lookup, leaving meaningful gaps for an agent consuming 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?

Schema description coverage is 100%: both 'email' and 'check_mx' have meaningful descriptions. The tool description reiterates the live MX check but adds no additional parameter-level semantics, such as accepted email formats or how check_mx affects the overall verification flow.

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 'B2B email and deliverability verifier' and enumerates specific functions: RFC 5322 syntax validation, live DNS MX verification, disposable domain detection, and reputation scoring. This clearly differentiates verify_email from its siblings (e.g., lookup_ip, repair_json), which address unrelated concerns.

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 context for when to invoke the tool: verifying B2B email addresses and assessing deliverability. However, it does not explicitly state when not to use it or mention alternative tools, though the sibling list contains no competing email tools.

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