ai-crawler-readiness

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

With no annotations, the description carries the full burden, and it does substantial work: it discloses that the tool makes real HTTP requests, that Google-Extended and Applebot-Extended are treated as robots-only tokens with no server verdict, and that they are excluded from server-side counts. It does not mention failure modes, rate limits, or side effects, but the core behavior is clearly exposed.

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?

Every clause earns its place: it front-loads the tool's purpose, then explains the measurement method, the robots-token edge case, and the structure of `fixes`. Despite its length, nothing is redundant and the structure moves from output to method to caveats.

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 must define the return contract, and it covers the score, per-crawler verdicts, edge vendor, and fixes with important caveats. It stops short of describing exact response formatting, error behavior, or what happens on unreachable hosts, but for a one-parameter measurement tool the essentials are present.

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 documents `host` clearly with the bare-domain requirement and an example, so schema coverage is 100%. The description adds domain-specific context but no new parameter semantics, 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 opens with a concrete evaluation question and then enumerates specific outputs: readiness score, per-crawler verdicts with the three possible values, the answering edge vendor, and the `fixes` list. This makes the tool's function unambiguous and distinct from generic domain-measurement tools, even though sibling names are not mentioned.

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 a measured readiness answer based on real HTTP requests rather than guesses from robots.txt alone. However, it never names the sibling tools or states when not to use this tool, leaving the routing decision to the agent.

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 behavioral burden. It adds rich interpretive context: the distinction between a 'blanket wall' and a 'managed block list', and the meaning of the contradiction rate as an infrastructure default. It does not mention read-only nature or side effects, but for an analytics tool this is adequately covered by the described output intent.

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 each earn their place: the first defines the core metric, the second explains the crawler breakdown and its analytical value. It is detailed but not bloated; however, the second sentence is somewhat dense and could be split without losing meaning.

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 a single optional parameter and no output schema, the description covers the essential context: the variables involved (vendor, crawler, contradiction rate), the threshold logic (in schema), and the interpretation. It does not spell out the exact response structure, but the dimensions are clearly implied, making it complete enough for 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 sole parameter `limit` has a 100% descriptive schema entry explaining its default and the 200-pair threshold. The main description adds no parameter-specific detail, so the baseline 3 for full schema coverage 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 clearly defines the tool's output: per CDN/WAF vendor, the share of domain-crawler pairs that robots.txt allows but the server blocks, with a crawler-level breakdown. It goes beyond naming the metric by explaining how to interpret it ('infrastructure default vs. site owner decision'), making it unambiguous and distinct from sibling tools like domain_readiness or web_openness.

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 fully explaining what the tool measures, but it never explicitly states when to use this tool over siblings or when not to use it. There are no exclusions or alternative recommendations, so the agent must infer context from the metric description 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 provided, the description carries the behavioral burden. It clearly discloses that the tool performs 9 real outbound HTTP requests, lists the user-agent composition and resource types, and indicates that results come from a fresh measurement rather than cached data. It does not mention potential latency, rate-limit considerations, or whether results are persisted, but the core behavioral profile is well disclosed.

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, each earning its place: the first defines the action precisely, the second gives usage direction, and the third explains the return value. There is no filler or duplication of schema content.

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 absence of an output schema, the description adequately explains the return by referencing the same `fixes` list as domain_readiness. It also supplies the request composition, usage conditions, and the distinction from archive data. It could be more complete by describing what the fixes list contains, but it is sufficient for an agent to invoke the tool 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 coverage is 100%, so both parameters (host and force) are already fully described in the input schema. The description adds useful context about when a fresh measurement matters (after robots.txt/WAF changes), but it does not materially extend the parameter semantics beyond what the schema already provides. Baseline 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 opens with a specific verb and resource ('Measure a domain') and immediately differentiates the tool from its archive-based alternative ('instead of reading the archive'). It also enumerates the exact measurement behavior (9 HTTP requests, specific user-agents, and resource types), so an agent clearly knows what this tool does and how it differs from domain_readiness.

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 gives explicit when-to-use guidance: 'Use it for any site the index has not reached yet, or when the caller wants a fresh verdict after changing robots.txt or a WAF rule.' It also states the alternative behavior ('instead of reading the archive'), which helps the agent choose between this tool and the archive-based sibling.

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 burden of behavioral disclosure. It clearly explains that the data is a before/after diff from the index's own requests and cannot be reconstructed from public sources. This is meaningful provenance information beyond the schema.

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 compact, front-loaded with the core 'what changed' purpose, and every sentence adds value: the uniqueness explanation and concrete use cases are both useful. No filler or repetition.

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 output semantics well for a tool with no output schema: domains, flip day, and robots.txt/edge distinction. The only minor gap is that 'a specific AI crawler' is mentioned but the input schema has no crawler parameter, leaving some ambiguity about how the agent selects which crawler's changes are returned.

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 days, host, and limit. The description adds no new parameter-level details, which is fine because the baseline of 3 applies when the schema covers all 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 states exactly what the tool does: it reports domains that recently started or stopped blocking a specific AI crawler, when the flip was observed, and whether the change was in robots.txt or at the edge. This is specific enough to distinguish it from sibling tools focused on static readiness or blocking state.

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 explicit use cases: answering 'who just blocked/unblocked ChatGPT, Claude, Perplexity...' and watching a single domain over time. It does not explicitly name alternatives or exclusions, but the intended context is clear.

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 burden of explaining behavior. It reveals that the tool reports aggregate shares and per-crawler breakdowns, and suggests a current-snapshot view with 'right now.' However, it does not clarify how 'served,' 'robots-blocked,' or 'edge-blocked' are determined, what data source or measurement window is used, or whether any operational constraints apply.

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 entire description is one focused, front-loaded sentence. It packs the metric's scope, blocking criterion, and per-crawler breakdown without filler or repetition.

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 parameterless metric tool, the description conveys the main output and scope, and no output schema exists to fill gaps. Still, it leaves the exact meaning of the breakdown categories and the relationship to sibling tools like domain_readiness and edge_blocking unspecified, so an agent may need additional inference.

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 and 100% schema coverage, so there is no parameter documentation burden. The description appropriately focuses on output semantics rather than parameter details, which matches the baseline for a parameterless 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 clearly identifies the tool's subject: the share of measured top domains readable by AI assistants and a per-crawler breakdown of served, robots-blocked, and edge-blocked states. It is specific and distinct from the aggregate scope, though it lacks an explicit action verb like 'returns' or 'calculates'.

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 the tool is for assessing overall web openness across measured domains, but it never explicitly says when to choose this tool over siblings like domain_readiness or edge_blocking. There is no when-not-to-use guidance or named alternatives.

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