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

With no annotations, the description carries the full burden and does so thoroughly: read-only traversal, strict domain-boundary enforcement, API key requirement, credit billing (including failed-page exemption), JS rendering with anti-bot bypass, and error-return behavior. This is exactly the behavioral context an agent needs before invoking a crawl that consumes credits.

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?

Front-loaded purpose sentence followed by labeled sections (BEHAVIOR & SAFETY, AUTHENTICATION, RATE LIMITS & BILLING, etc.). Every section conveys actionable information; there is 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?

Although there is no output schema, the description explains that output is aggregated Markdown or structured error JSON, and it covers auth, billing, domain scoping, and JS rendering. With all three parameters fully schema-documented, an agent has everything needed to call this 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%, so url, depth, and limit are already fully documented in the schema. The description alludes to 'configured depth and page limit' but adds no syntax, range, or interaction details beyond what the schema states, 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?

States a specific verb and resource ('recursively crawl multiple pages of an entire website') along with scope constraints (depth, page limit, internal links). It also explicitly distinguishes itself from flycrawl_map, so an agent can tell them apart without opening either schema.

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 'DIFFERENCE FROM flycrawl_map' section gives explicit routing guidance between two closely related tools. However, it does not address when to prefer flycrawl_scrape, flycrawl_search, or flycrawl_extract, leaving some sibling selection to inference.

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 does so: read-only/idempotent, required API key, 1-credit cost with a no-charge guarantee on failure/timeout/5xx, dynamic JS execution and anti-bot behavior, and an explicit error shape without unhandled exceptions. These are behavioral facts an agent cannot infer from 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?

Front-loaded purpose sentence followed by labeled blocks that make scanning cheap. It is slightly longer than necessary — the billing guarantee and anti-bot detail are dense — but each block carries distinct, decision-relevant information rather than restating the 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?

No output schema exists, and the description partially compensates by describing both success semantics (validated JSON per schema) and the failure envelope. The remaining gap is how results are wrapped relative to the supplied schema, which an agent would still have to discover empirically.

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 all three parameters (url, prompt, schema) are already documented in the input schema. The description reinforces the natural-language + JSON Schema combination but adds no format, precedence, or conflict guidance (e.g., what happens when prompt and schema disagree). 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?

Opens with a specific verb and resource: 'Extract typed, structured JSON entities from any live webpage,' plus the mechanism (natural-language guidance + optional JSON Schema). It also explicitly names the sibling it is not (flycrawl_scrape), so an agent can differentiate without opening either schema.

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 'DIFFERENCE FROM flycrawl_scrape' block gives the exact selection rule: whole-page cleaned Markdown vs LLM-parsed validated JSON. That is a genuine alternative-plus-condition. It stops short of exclusions (e.g., auth-gated pages, non-HTML targets), which keeps it below a 5.

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 present, the description carries the full burden and does so: it declares read-only/non-destructive behavior, the data sources queried (sitemaps, robots.txt, link graphs), API-key auth, cost of 1 credit per operation, JS-rendering behavior, and error semantics. It even discloses the return shape (URLs only, no content bodies).

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 labeled sections are front-loaded and scannable, and each line adds information rather than restating the schema. The 'under 2 seconds' performance claim is slightly promotional and not load-bearing.

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 3-parameter read tool with no output schema, the description covers purpose, safety, auth, cost, return content, and error behavior — everything an agent needs to decide to call it and interpret results.

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 url, limit, and search are already fully documented in the schema. The description adds no parameter-level detail (e.g., what 'search' filters against or how limit truncates), so the 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?

States a specific verb and resource: 'discover and list all reachable internal URLs and sitemap hierarchy on a domain.' It also explicitly contrasts itself with flycrawl_crawl, so an agent can distinguish it from the closest sibling without opening either schema.

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?

Provides a clear use case ('reconnaissance before targeted scraping') and names the alternative it is not (flycrawl_crawl, which returns content bodies). It does not address the other siblings (flycrawl_search, flycrawl_scrape, flycrawl_extract), so the routing guidance is strong but not exhaustive.

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 burden and does so: read-only/idempotent, API key requirement, 1 credit per successful scrape with a no-charge guarantee on 4xx/5xx and timeouts, cache TTL cost behavior, JS rendering and anti-bot handling, and structured error returns. This is unusually rich behavioral context for a tool with zero annotation 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?

Section labels (BEHAVIOR & SAFETY, AUTHENTICATION, RATE LIMITS, DIFFERENCE FROM) make it scannable and front-loaded with the purpose. It is longer than strictly necessary, and the format enumeration at the top is incomplete relative to the schema, but each block carries actionable 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?

With four parameters, no output schema, and no annotations, the description covers auth, cost, rendering, error format, and sibling differentiation adequately. The only shortfall is the incomplete output-format list, leaving the agent to discover summary and html from the 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 100%, so the baseline is 3; the description adds value by explaining the billing implication of caching (cached requests cost 0 credits), which the maxAge schema does not state. It lists markdown/json/links but omits the summary and html enum values, a small gap rather than a contradiction.

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?

States a specific verb (scrape) and resource (single webpage) plus the concrete output artifacts (Markdown, JSON, links). It explicitly names the sibling flycrawl_extract and the boundary between them, so an agent can distinguish the two without opening either schema.

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?

Gives an explicit routing rule: use flycrawl_extract for schema-conforming JSON fields, this tool for full readable page text. It lacks guidance on when to prefer flycrawl_search, flycrawl_crawl, or flycrawl_map for multi-page work, but the primary alternative is clearly framed.

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 and does: it declares read-only live behavior, the FLYCRAWL_API_KEY requirement, 1-credit-per-request billing, ad/sponsored-link stripping, and the error return shape. That is authorization, cost, and failure-mode disclosure an agent needs before calling a billable external 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?

Front-loaded lead sentence followed by clearly labeled sections, so scanning is fast. The labeled blocks are slightly ceremonial for a two-parameter tool, but every line conveys distinct information with 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?

No output schema exists, and the description compensates by stating the return is Markdown summaries or structured error JSON. Combined with auth, cost, and freshness notes, nothing essential for a correct call is missing.

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 both 'query' and 'limit' are already documented in the schema. The description adds only indirect hints ('top search results', 'result summaries') and no format or syntax guidance beyond that, so the 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?

States a specific verb+resource (search the live web) plus the distinguishing behavior (auto-scraping top results into Markdown in one call). The explicit 'DIFFERENCE FROM flycrawl_scrape' line lets an agent separate this from its closest sibling without opening either schema.

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?

Explicitly contrasts keyword-driven search with URL-driven scrape, which is precisely the selection decision an agent must make among these siblings. No exclusions are stated for the remaining siblings, but the primary ambiguity is resolved directly.

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