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

With no annotations, the description carries the burden of behavioral disclosure. It clearly states that disclaimers/prohibitions are not flagged, which is a meaningful behavioral nuance. It also notes that HTML tags are ignored, which is a useful input-handling detail. It does not disclose output format or whether the tool returns matches, counts, or a pass/fail, but the core behavior is transparent enough for a scanning 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?

Two sentences, no filler, and the key scoping information is front-loaded. The first sentence defines the target precisely; the second sentence clarifies an important exclusion. Every word earns its place.

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 scanning tool with no output schema, the description is nearly complete. It tells the agent what to scan for, what not to flag, and how the input is handled. The only missing piece is what the tool returns (e.g., list of flagged phrases, boolean, count), but that is not required by the rubric since there is no output schema. Still, a brief note on return format would make it fully 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?

Schema coverage is 100% and the single parameter 'text' is described as 'Plain text or HTML. HTML tags are ignored.' The description adds context about what kind of text is relevant (copy with performance claims) and the exclusion of disclaimers, which goes beyond the schema. Since there is only one parameter and the schema already covers it, the description's additional context earns a 4.

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 states a specific verb ('scan'), a specific resource ('copy'), and a precise target ('affirmative performance claims' in finance, gambling, and health advertising). It also explicitly excludes disclaimers/prohibitions, which distinguishes it from a generic keyword checker. This is a clear, specific purpose that an agent can act on.

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 this tool: when you need to detect affirmative performance claims in copy, especially in regulated advertising contexts. It does not explicitly name alternatives or state when not to use it, but the sibling list (check_keywords, check_translation, etc.) and the specific claim-focused language make the intended use clear. A small gap: no explicit 'use check_keywords for simple keyword matching' 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?

No annotations are provided, so the description carries the burden. It discloses a key behavioral trait: links inside excluded boilerplate do not count, and explains why. It also clarifies that 'Contact us for a quote' is not an offer, which is a useful semantic behavior. It doesn't mention return format or side effects, but for a read-only check tool this is acceptable.

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 main purpose, and the second sentence earns its place by explaining a non-obvious behavioral rule. 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 read-only validation tool with 6 parameters and no output schema, the description covers the main behavioral nuance (boilerplate exclusion) and the optional figure requirement. It doesn't describe the return value, but that's often acceptable for a check tool. The main gap is not stating what the tool returns (e.g., boolean, list of failures), but the description is otherwise complete enough for an agent to call it correctly.

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 83%, so the schema already documents most parameters. The description adds meaning by explaining the purpose of exclude_classes (site-wide CTA blocks) and the semantic of require_figure ('Contact us for a quote' is not an offer). This goes beyond the schema's literal 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 states a specific verb ('Check') and resource ('content page links to at least one commercial page from its body'), and adds a concrete optional condition ('states a concrete figure'). It clearly distinguishes itself from sibling tools like check_keywords or check_claims by focusing on internal link structure and commercial intent.

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 explains the core use case and the rationale for excluding boilerplate, which implies when to use it (content pages) and why exclude_classes matters. It doesn't explicitly name alternatives or say when not to use it, but the context is clear enough for an agent to select it over siblings.

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 carries the full transparency burden. It discloses important behavioral nuances: literal case-insensitive matching, whitespace not normalized, and the special rule for highest-search-volume terms. It stops short of describing the return value, but the core verification behavior is clearly explained.

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 sentences deliver purpose, threshold behavior, and matching semantics with no filler. The most important action is front-loaded, and every sentence adds distinct 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?

Input semantics are well covered, but there is no output schema and the description does not state what the tool returns (boolean, counts, missing keywords, etc.). Minor edge cases like empty keyword maps or invalid HTML are also unaddressed, leaving some uncertainty for an 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?

The description adds real meaning beyond the schema by explaining how keyword search volumes determine which terms require primary_min_hits. It also clarifies that term matching is literal and case-insensitive, which directly informs how the keywords map is interpreted. Other parameters rely on the schema, but schema coverage is already high.

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?

Description opens with a clear verb and resource: 'Verify that target keywords actually appear in a rendered page.' It is easily distinguished from siblings such as check_translation, check_internal_links, and check_claims, which address different page qualities.

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 intended use is implied: call this tool when you need to confirm keyword presence in rendered HTML. However, the description never explicitly says when to prefer it over alternatives or when not to use it, so routing guidance is weak.

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 behavioral disclosure burden. It details the specific checks performed and explicitly states what the tool does not do, which is valuable transparency. It stops short of describing the output format or any error conditions, but for a read-only comparison tool this is substantial coverage.

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 no filler. The first sentence front-loads the core purpose and then lists the concrete checks, while the second sentence immediately clarifies the tool's limitation. Every word earns its place.

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 is strong on scope and limits, but because there is no output schema, it does not explain the return value or how the agent should interpret the results. An agent invoking this tool would not know whether it returns a boolean, a list of mismatches, or a detailed report, which is a meaningful gap for a tool with no output schema.

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 83%, and the schema already documents parameters like locale, forbid_source_script, and require_front_matter well. The description adds context around what 'structural drift' means and references locale prefixes and source-script characters, mildly reinforcing parameter intent, but it does not add significant new semantic detail beyond the schema.

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 ('Compare') and resource ('a translation against its source document') and enumerates the exact structural dimensions checked. It also explicitly distinguishes this from meaning-based evaluation, which helps separate it from the sibling check_* 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 clearly states the tool's scope ('structural drift') and its limitation ('cannot tell you a translation is good'), which gives a strong when-to-use signal. It does not explicitly name alternative tools, but the 'not meaning' exclusion effectively guides the agent away from using it for semantic checking.

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 behavioral disclosure burden. It does disclose a key trait: volatile blocks and scripts are removed before hashing. However, it does not state whether the hash is deterministic, what algorithm is used, what the return value looks like, or whether the operation has side effects.

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, zero filler. The operation is first, the use case second. Every word earns its place.

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?

Although the tool's concept is simple, the missing parameter explanations and lack of any return-value description leave an agent under-informed. For a tool with no annotations and no output schema, the description should at least connect strip_classes/strip_patterns to the stripping behavior and indicate the type of result produced.

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 0%, yet the description mentions none of the three parameters by name. 'body' is only indirectly implied by 'content of a page', and 'strip_classes' and 'strip_patterns' — which presumably customize the volatile-block removal — are completely unexplained, forcing the agent to guess their 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 states a specific verb and resource ('Hash the meaningful content of a page') with a defining behavioral qualifier ('with volatile blocks and scripts removed'). It also gives the outcome ('tell a real edit from a rebuild'), which clearly differentiates it from the sibling check_* 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 phrase 'Use it to tell a real edit from a rebuild' gives a concrete, actionable scenario for when this tool is appropriate. It does not explicitly name alternatives or exclusions, but the use case is specific enough that an agent can judge when to reach for it.

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 disclosure burden. It does transparently reveal the core decision logic — content is hashed, compared to the stored hash, and the date advances only on real change — which is the tool's essential behavioral trait. But it omits the return value format, first-seen behavior when previous_hash is null, and failure modes for malformed strip_patterns.

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 sentences with the purpose front-loaded in the first, the mechanism in the second, and a brief rationale in the third that explains why the behavior matters. No filler; every sentence earns its place.

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 has 6 parameters, no annotations, and no output schema, so the description must disclose the return contract — but it never states what the function returns (a date string? a boolean? a full update?) or how it handles first-run cases (null previous_hash / null previous_lastmod). These are essential for an agent to invoke it correctly.

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%, putting the baseline at 3. The description's narrative adds an interaction model beyond the individual schema entries: body is hashed after stripping, compared against previous_hash, and previous_lastmod advances to today only on genuine change. This workflow-level meaning connects the parameters in a way the schema alone does not.

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 states a specific verb-resource pair — 'Decide a sitemap lastmod date honestly' — and explains the mechanism (hash content, compare with stored hash, move the date only on genuine change). This clearly differentiates the tool from sibling check_* tools and content_hash: the siblings inspect content or compute hashes, while this one decides a date.

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 use case is implied — computing honest lastmod dates during sitemap builds — and the anti-pattern ('Stamping today's date on every URL every build') is described well. However, the description never explicitly names an alternative or states when not to use this tool (e.g., when only a raw hash is needed, use content_hash), leaving the routing guidance implicit.

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