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

No annotations exist, so the description carries the full burden. It usefully discloses that the result reflects a fresh circuit (so the IP may differ per call), which is real behavioral context beyond the name. However, it omits whether this makes a network request, its latency, or whether repeated calls rotate the exit node.

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?

A single front-loaded sentence with zero filler. The core answer (the public IP destinations see) comes first and the qualifier is parenthetical.

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 no parameters and no output schema, the description supplies what is needed: it names the returned value and its source. Slightly more on return type/format or circuit freshness semantics would make it fully self-contained.

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 takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. The description correctly signals a no-input utility rather than leaving the empty schema unexplained.

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?

Specific verb ('Return') plus precise resource ('the public IP address that destinations see'), with the parenthetical clarifying it is the Tor exit node. No sibling (fetch_page, search_onion, download_file, extract_links, page_metadata) performs this function, so the agent can distinguish it immediately.

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?

No explicit when-to-use or when-not-to-use guidance and no named alternatives, but the purpose is self-evident enough that usage is strongly implied. A brief note such as 'call this to verify your apparent IP before fetching a page' would raise 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 burden and does disclose real behavior: transfers route through Tor, writes land in TOR_DOWNLOAD_DIR, and existing files are never overwritten (an important, non-obvious safety trait). It omits auth needs, size/time limits, timeout behavior, and failure modes, keeping it short of a 5.

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 tight sentences with zero waste: destination and mechanism first, then the output_path semantics and overwrite policy. Every clause 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?

Covers both parameters, the destination, transport, and overwrite policy, which is solid for a 2-param tool. However, with no output schema and no annotations, the description should say what the call returns (e.g. the saved path) and any practical limits, which it does not.

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 are already documented, including that output_path is relative. The description largely restates that (relative to TOR_DOWNLOAD_DIR) and adds only the no-overwrite behavior; baseline 3 is appropriate when the schema does the heavy lifting.

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?

Names a specific verb (download), the resource types (document, image, archive, data file), the transport (through Tor), and the destination (TOR_DOWNLOAD_DIR). An agent can distinguish this from fetch_page, which retrieves page content rather than persisting a file.

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?

Usage is implied rather than stated: the mention of 'download directory' and 'through Tor' signals this is the file-persisting option versus fetch_page, but no explicit when-to-use, prerequisites, or alternative is named. Adequate but with a clear 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?

With no annotations, the description carries the full burden and does well: it discloses the no-network guarantee, the default .onion-only filtering, and the post-processing behavior ('deduplicated and grouped by host'). It stops short of error/edge-case behavior (malformed HTML, the 500k length cap), so not a 5.

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 tight sentences, front-loaded with purpose and the most consequential constraint (no network access), then parameter guidance, then output shape. No filler and nothing buried.

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-param, no-output-schema tool this is nearly complete: it covers the safety/scope trait, defaults, and result structure. Only minor edge-case behavior (input size limits, malformed input handling) is left unaddressed, which the schema partially covers via maxLength.

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% and the schema already documents all three parameters, including the filter_onion default and base_url's role. The description's restatement adds no syntax or format detail beyond what the schema provides, 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 ('Extract links from HTML') and immediately scopes it with '(no network access)', which cleanly separates it from fetch_page/download_file in the sibling set. An agent can tell at a glance that this is pure parsing, not retrieval.

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 how to steer behavior ('set filter_onion: false for all links', 'Pass base_url to resolve relative links'), which is useful operational guidance. However, it never says when to choose this tool over siblings such as page_metadata or fetch_page, nor any precondition beyond the implied need for HTML in hand.

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 usefully discloses Tor routing, text-vs-raw output, supported methods, and that session_id gives sticky circuits and cookies, but it omits rate limits, timeouts, error behavior, and whether requests are logged or authenticated.

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 tight sentences that front-load the core action and return value, then append the method and session capabilities. No filler and no repetition 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?

No output schema exists, but the description does explain the return value (text or raw HTML), which is the key thing an agent needs. For a 6-param fetch tool the coverage is solid, though error/timeout behavior 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 every parameter, making 3 the baseline. The description restates the method enum and raw/session behavior but adds little syntax or format meaning 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 states a specific verb and resource (fetch an HTTP(S)/.onion page through Tor) plus the return format (text or raw HTML). It implicitly separates itself from download_file and page_metadata by emphasizing page text retrieval, but it does not name or contrast any sibling explicitly.

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?

Usage is only implied by the capability statement; there is no explicit 'use this when...' guidance nor any mention of when to prefer extract_links, page_metadata, or download_file instead. An agent can infer the general context but must reason about the boundaries itself.

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 it does disclose a key behavioral trait: the tool performs no network access, making it a pure parse of supplied input. It also enumerates the extracted categories, effectively describing the return surface. It stops short of stating determinism, malformed-HTML handling, or size limits (the 500000 cap lives only in 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?

A single front-loaded sentence that packs the operation, the constraint, and the output inventory with zero filler. Every clause earns its place and the most decision-relevant fact ('no network access') appears early.

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 pure HTML-parsing utility with no output schema, the description covers the essentials: what it consumes, that it needs no network, and what it returns. The only gap is that the return values are named but not shaped, which is a minor omission for a summariser whose output is self-describing.

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 parameters are already documented, including the url field's role in internal/external link classification. The description adds no syntax, format, or edge-case meaning beyond that. Baseline 3 applies when the schema does the heavy lifting.

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 ('Summarise') and resource ('HTML'), then enumerates exactly what is extracted (title, description, H1/H2/H3, link counts, forms, meta tags). The parenthetical 'no network access' cleanly distinguishes it from fetch_page, so an agent can route between them 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?

'No network access' implies the caller must already hold the HTML (i.e., fetch it via fetch_page first), but this is left to inference rather than stated. No sibling is named and no when-not-to-use condition is given. Adequate implied usage, but not explicit routing 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 full burden. It does usefully disclose that traffic stays entirely inside Tor and that results mix clearnet and .onion sites, plus the return shape (titles, URLs, snippets). It says nothing about rate limits, DuckDuckGo throttling/blocking, failure modes when Tor is down, or whether the call is a safe read-only operation.

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 tight sentences, zero filler, and the mechanism/scope (Tor-only, .onion endpoint) is front-loaded before the return-value detail. Every clause 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 simple two-parameter read tool with full schema coverage and no output schema, the description covers the essentials: mechanism, routing, and return fields. It is only slightly short of complete because it omits operational caveats (Tor availability, rate limiting) that an agent might need to handle failures.

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% and both parameters (query, limit) are documented in the schema with defaults and bounds. The description adds no further semantics about query syntax or limit behavior, 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 names a specific verb (search) and resource (the web, via DuckDuckGo's .onion service), so an agent immediately knows this is a search tool rather than a page-fetching tool. It does not explicitly contrast itself with siblings like fetch_page or extract_links, but the 'search' framing is unambiguous enough to separate it.

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?

Usage is only implied: the agent can infer you call this to discover URLs and then use fetch_page/extract_links on the results. There is no explicit when-to-use statement, no mention of prerequisites (e.g., that a working Tor circuit is required, which check_exit_ip hints at), and no guidance on when another sibling is preferable.

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